@mmerterden/multi-agent-pipeline 12.6.0 → 12.8.0

package/pipeline/scripts/eval-mine-corpus.mjs

@@ -1,201 +0,0 @@
-#!/usr/bin/env node
-// eval-mine-corpus.mjs  -  grow the triage eval set from real production runs.
-//
-// The pipeline already records every Phase 4 triage decision to the per-repo
-// `~/.claude/memory/multi-agent/<repo-slug>/triage-corpus.jsonl` (one line per finding:
-// severity/file/line/issue/fix/reviewer + the classification the run gave it,
-// plus an optional human `reason`/`reviewer`). Hand-authoring eval fixtures is
-// the bottleneck; this closes the loop by turning those real decisions into
-// CANDIDATE regression fixtures in the exact shape `eval-triage.mjs` consumes.
-//
-// It is review-gated on purpose: candidates land in
-// `pipeline/eval/triage-candidates/<task_id>/` (which eval-triage does NOT
-// walk), each validated against the triage schema. A maintainer reviews them,
-// fills scope/diffSummary, and moves the good ones into
-// `pipeline/eval/triage/<NN>-<name>/` to adopt them.
-//
-// Highest-signal cases (a human left a `reason` or `reviewer`) are emitted
-// first and marked, since those encode a deliberate triage judgement.
-//
-// Usage:
-//   node pipeline/scripts/eval-mine-corpus.mjs                 # default corpus path
-//   node pipeline/scripts/eval-mine-corpus.mjs --corpus <path>
-//   node pipeline/scripts/eval-mine-corpus.mjs --limit 20      # cap candidates
-//   node pipeline/scripts/eval-mine-corpus.mjs --dry-run       # report, write nothing
-//
-// Exit codes: 0 ok (including "nothing to mine"), 2 usage/setup error.
-
-import { readdirSync, readFileSync, writeFileSync, mkdirSync, existsSync } from "node:fs";
-import { dirname, join, resolve } from "node:path";
-import { fileURLToPath } from "node:url";
-import { homedir } from "node:os";
-import { spawnSync } from "node:child_process";
-
-const here = dirname(fileURLToPath(import.meta.url));
-const root = resolve(here, "..", "..");
-const evalTriageDir = join(root, "pipeline", "eval", "triage");
-const candidatesDir = join(root, "pipeline", "eval", "triage-candidates");
-const validator = join(root, "pipeline", "scripts", "validate-triage.mjs");
-
-const args = process.argv.slice(2);
-const opts = { corpus: null, limit: Infinity, dryRun: false, repoSlug: null };
-for (let i = 0; i < args.length; i++) {
-  if (args[i] === "--corpus") opts.corpus = args[++i];
-  else if (args[i] === "--repo-slug") opts.repoSlug = args[++i];
-  else if (args[i] === "--limit") opts.limit = Number(args[++i]) || Infinity;
-  else if (args[i] === "--dry-run") opts.dryRun = true;
-  else if (args[i] === "-h" || args[i] === "--help") {
-    console.log("Usage: eval-mine-corpus.mjs [--corpus <path>] [--repo-slug <slug>] [--limit N] [--dry-run]");
-    process.exit(0);
-  }
-}
-
-// Resolve the corpus path the SAME way triage-memory.mjs writes it:
-// ~/.claude/memory/multi-agent/<repo-slug>/triage-corpus.jsonl (per repo).
-// (The old default read ~/.claude/logs/.../triage-corpus.jsonl - a flat path
-// nothing writes to - so without --corpus it always found nothing.)
-function resolveRepoSlug() {
-  if (opts.repoSlug) return String(opts.repoSlug);
-  if (process.env.MULTI_AGENT_REPO_SLUG) return process.env.MULTI_AGENT_REPO_SLUG;
-  const r = spawnSync("git", ["rev-parse", "--show-toplevel"], { encoding: "utf-8" });
-  if (r.status === 0 && r.stdout.trim()) return r.stdout.trim().split("/").pop();
-  return "default";
-}
-
-const corpusPath =
-  opts.corpus ||
-  join(homedir(), ".claude", "memory", "multi-agent", resolveRepoSlug(), "triage-corpus.jsonl");
-
-if (!existsSync(corpusPath)) {
-  console.log(`eval-mine-corpus: no corpus at ${corpusPath} - nothing to mine.`);
-  process.exit(0);
-}
-
-// Parse the JSONL corpus, skipping blank/malformed lines (never crash on data).
-const rows = [];
-for (const line of readFileSync(corpusPath, "utf-8").split("\n")) {
-  const s = line.trim();
-  if (!s) continue;
-  try {
-    const r = JSON.parse(s);
-    if (r && r.task_id && r.issue && r.classification) rows.push(r);
-  } catch {
-    /* skip malformed line */
-  }
-}
-
-if (rows.length === 0) {
-  console.log("eval-mine-corpus: corpus has no usable rows - nothing to mine.");
-  process.exit(0);
-}
-
-// task_ids that already have an adopted fixture: skip so we only propose new cases.
-const adopted = new Set();
-if (existsSync(evalTriageDir)) {
-  for (const name of readdirSync(evalTriageDir)) {
-    const inputPath = join(evalTriageDir, name, "input.json");
-    if (existsSync(inputPath)) {
-      try {
-        const meta = JSON.parse(readFileSync(join(evalTriageDir, name, "meta.json"), "utf-8"));
-        if (meta.task_id) adopted.add(meta.task_id);
-      } catch {
-        /* no meta.json -> can't dedup by task_id, that's fine */
-      }
-    }
-  }
-}
-
-// Group corpus rows by task_id.
-const byTask = new Map();
-for (const r of rows) {
-  if (!byTask.has(r.task_id)) byTask.set(r.task_id, []);
-  byTask.get(r.task_id).push(r);
-}
-
-const toFinding = (r) => ({
-  severity: r.severity,
-  file: r.file,
-  // Triage contract requires an integer line >= 0; corpus may carry null for a
-  // file-level finding, so coerce to 0 (the schema's file-level sentinel).
-  line: Number.isInteger(r.line) ? r.line : 0,
-  issue: r.issue,
-  fix: r.fix ?? null,
-  reviewer: r.reviewer ?? null,
-});
-
-// Build a candidate per task. Highest-signal first (has a human reason/reviewer).
-const candidates = [];
-for (const [taskId, findings] of byTask) {
-  if (adopted.has(taskId)) continue;
-  const rawFindings = findings.map(toFinding);
-  const accepted = [];
-  const deferred = [];
-  const rejected = [];
-  for (const r of findings) {
-    if (r.classification === "accepted") accepted.push(toFinding(r));
-    else if (r.classification === "deferred")
-      deferred.push({ finding: toFinding(r), reason: r.reason || "TODO: reason (from corpus)" });
-    else if (r.classification === "rejected")
-      rejected.push({ finding: toFinding(r), reason: r.reason || "TODO: reason (from corpus)" });
-  }
-  const hasHumanSignal = findings.some((r) => r.reason || r.reviewer);
-  const title = findings.find((f) => f.task_title)?.task_title || taskId;
-  candidates.push({
-    taskId,
-    hasHumanSignal,
-    input: {
-      rawFindings,
-      // Corpus does not record scope/diff; a maintainer fills these before adopting.
-      scope: `TODO: scope for ${title}`,
-      diffSummary: "TODO: diff summary",
-    },
-    expected: {
-      accepted,
-      deferred,
-      rejected,
-      // Blockers loop back to dev, so a run with an accepted blocker is not approved.
-      approved: accepted.every((f) => f.severity !== "blocking"),
-    },
-  });
-}
-
-candidates.sort((a, b) => Number(b.hasHumanSignal) - Number(a.hasHumanSignal));
-const selected = candidates.slice(0, opts.limit);
-
-if (selected.length === 0) {
-  console.log("eval-mine-corpus: no new task_ids to propose (all already adopted).");
-  process.exit(0);
-}
-
-let written = 0;
-let invalid = 0;
-for (const c of selected) {
-  const safe = c.taskId.replace(/[^A-Za-z0-9._-]/g, "_");
-  const dir = join(candidatesDir, safe);
-  const tag = c.hasHumanSignal ? " [human-signal]" : "";
-  if (opts.dryRun) {
-    console.log(`  would emit candidate: ${safe} (${c.input.rawFindings.length} findings)${tag}`);
-    continue;
-  }
-  mkdirSync(dir, { recursive: true });
-  writeFileSync(join(dir, "input.json"), JSON.stringify(c.input, null, 2) + "\n");
-  writeFileSync(join(dir, "expected.json"), JSON.stringify(c.expected, null, 2) + "\n");
-  writeFileSync(
-    join(dir, "meta.json"),
-    JSON.stringify({ task_id: c.taskId, source: "eval-mine-corpus", hasHumanSignal: c.hasHumanSignal }, null, 2) + "\n",
-  );
-  // Validate the emitted expected.json against the triage contract; flag if bad.
-  const res = spawnSync("node", [validator, join(dir, "expected.json")], { encoding: "utf-8" });
-  const ok = res.status === 0;
-  if (!ok) invalid++;
-  console.log(`  emitted: triage-candidates/${safe}${tag} ${ok ? "(schema OK)" : "(SCHEMA FAIL - review)"}`);
-  written++;
-}
-
-if (!opts.dryRun) {
-  console.log("");
-  console.log(`eval-mine-corpus: ${written} candidate(s) written to pipeline/eval/triage-candidates/`);
-  if (invalid > 0) console.log(`  ${invalid} failed schema validation - fix before adopting.`);
-  console.log("  Review each, fill scope/diffSummary, then move good ones into");
-  console.log("  pipeline/eval/triage/<NN>-<name>/ to add them to the eval suite.");
-}

package/pipeline/scripts/eval-triage.mjs

@@ -1,171 +0,0 @@
-#!/usr/bin/env node
-// eval-triage.mjs  -  semantic regression check for Phase 4 triage.
-//
-// Walks pipeline/eval/triage/<NN>-<name>/ subdirectories. For each case:
-//   1. Reads input.json (rawFindings + scope + diffSummary)
-//   2. Reads expected.json (the spec-defined triage output)
-//   3. Runs validate-triage.mjs against expected.json  -  must exit cleanly
-//   4. Asserts every rawFinding in input is accounted for in expected
-//      (sum of accepted + deferred[].finding + rejected[].finding == rawFindings)
-//   5. Asserts no inventions: every classified finding traces back to a
-//      raw finding by {file, line, issue} match.
-//
-// What this catches:
-//   - Spec drift: someone changes phase-4-review.md section3 in a way that contradicts
-//     a fixture without updating the fixture.
-//   - Schema drift: validate-triage.mjs starts rejecting fixtures that used
-//     to pass.
-//   - Coverage gap: input has N findings but expected only classifies M < N
-//     (a real triage agent doing the same would silently lose findings).
-//
-// What this does NOT catch:
-//   - Whether a real triage agent would actually produce the expected output.
-//     That requires API keys + nondeterminism. Use a separate eval harness
-//     for that. This is a CONTRACT regression test, not a model-quality eval.
-//
-// Usage:
-//   node pipeline/scripts/eval-triage.mjs                   # all cases
-//   node pipeline/scripts/eval-triage.mjs --case 03-...     # one case
-//   node pipeline/scripts/eval-triage.mjs --json            # CI-friendly output
-//
-// Exit codes: 0 all pass, 1 one or more fail, 2 usage/setup error.
-
-import { readdirSync, readFileSync, statSync } from "node:fs";
-import { dirname, join, resolve } from "node:path";
-import { fileURLToPath } from "node:url";
-import { spawnSync } from "node:child_process";
-
-const here = dirname(fileURLToPath(import.meta.url));
-const root = resolve(here, "..", "..");
-const evalDir = join(root, "pipeline", "eval", "triage");
-const validator = join(root, "pipeline", "scripts", "validate-triage.mjs");
-
-const args = process.argv.slice(2);
-const opts = { json: false, case: null };
-for (let i = 0; i < args.length; i++) {
-  if (args[i] === "--json") opts.json = true;
-  else if (args[i] === "--case") opts.case = args[++i];
-  else if (args[i] === "-h" || args[i] === "--help") {
-    console.log("Usage: eval-triage.mjs [--case <name>] [--json]");
-    process.exit(0);
-  }
-}
-
-function listCases() {
-  return readdirSync(evalDir)
-    .filter((f) => f !== "README.md" && statSync(join(evalDir, f)).isDirectory())
-    .sort();
-}
-
-// Compare two finding records by stable-key triple.
-function findingKey(f) {
-  return `${f.file}::${f.line}::${f.issue}`;
-}
-
-function runCase(name) {
-  const dir = join(evalDir, name);
-  const inputPath = join(dir, "input.json");
-  const expectedPath = join(dir, "expected.json");
-  const errors = [];
-
-  let input, expected;
-  try {
-    input = JSON.parse(readFileSync(inputPath, "utf-8"));
-  } catch (e) {
-    return { name, ok: false, errors: [`input.json: ${e.message}`] };
-  }
-  try {
-    expected = JSON.parse(readFileSync(expectedPath, "utf-8"));
-  } catch (e) {
-    return { name, ok: false, errors: [`expected.json: ${e.message}`] };
-  }
-
-  // 1. Structural sanity via validate-triage.mjs.
-  const result = spawnSync("node", [validator, expectedPath], {
-    encoding: "utf-8",
-  });
-  // Validator exit codes: 0 valid+clean, 1 invalid, 2 over-rejection,
-  // 3 contradiction-corrected. For fixtures we expect 0 or 2 (over-rejection
-  // is structurally valid but caller must pause).
-  if (result.status !== 0 && result.status !== 2) {
-    errors.push(
-      `validator failed (exit ${result.status}); fixture must be either clean (0) or over-rejection (2). stderr: ${result.stderr.trim()}`,
-    );
-  }
-
-  // 2. Coverage: every rawFinding in input must appear once in expected.
-  const raw = input.rawFindings || [];
-  const rawKeys = new Set(raw.map(findingKey));
-  const seen = new Set();
-
-  function consume(f, where) {
-    const k = findingKey(f);
-    if (!rawKeys.has(k)) {
-      errors.push(`${where}: invented finding not in input ({${k}})`);
-      return;
-    }
-    if (seen.has(k)) {
-      errors.push(`${where}: duplicate classification of finding ({${k}})`);
-      return;
-    }
-    seen.add(k);
-  }
-
-  (expected.accepted || []).forEach((f) => consume(f, "accepted"));
-  (expected.deferred || []).forEach((d) => consume(d.finding, "deferred"));
-  (expected.rejected || []).forEach((d) => consume(d.finding, "rejected"));
-
-  // Anything in raw but not classified?
-  for (const r of raw) {
-    if (!seen.has(findingKey(r))) {
-      errors.push(`unclassified raw finding (lost): ${findingKey(r)}`);
-    }
-  }
-
-  // 3. Approved consistency: approved===true iff no accepted blocker.
-  const hasBlocker = (expected.accepted || []).some((f) => f.severity === "blocking");
-  if (expected.approved === true && hasBlocker) {
-    errors.push("approved=true but accepted contains a blocking finding");
-  }
-  if (expected.approved === false && !hasBlocker) {
-    errors.push("approved=false but accepted has no blocking finding");
-  }
-
-  return {
-    name,
-    ok: errors.length === 0,
-    errors,
-    rawCount: raw.length,
-    accepted: (expected.accepted || []).length,
-    deferred: (expected.deferred || []).length,
-    rejected: (expected.rejected || []).length,
-    approved: expected.approved,
-    validatorExit: result.status,
-  };
-}
-
-const cases = opts.case ? [opts.case] : listCases();
-if (cases.length === 0) {
-  console.error("No cases found under pipeline/eval/triage/");
-  process.exit(2);
-}
-
-const results = cases.map(runCase);
-const failed = results.filter((r) => !r.ok);
-
-if (opts.json) {
-  console.log(JSON.stringify({ total: results.length, failed: failed.length, results }, null, 2));
-} else {
-  for (const r of results) {
-    const mark = r.ok ? "✓" : "✗";
-    const tally = `raw=${r.rawCount} acc=${r.accepted} def=${r.deferred} rej=${r.rejected} approved=${r.approved} validator=${r.validatorExit}`;
-    console.log(`${mark} ${r.name.padEnd(34)} ${tally}`);
-    if (!r.ok) {
-      for (const e of r.errors) console.log(`    ${e}`);
-    }
-  }
-  console.log("");
-  console.log(`══ eval-triage: ${results.length - failed.length}/${results.length} passed ══`);
-}
-
-process.exit(failed.length === 0 ? 0 : 1);

package/pipeline/scripts/fixtures/diff-risk-android.diff

@@ -1,40 +0,0 @@
-diff --git a/app/src/main/java/com/example/auth/AuthRepository.kt b/app/src/main/java/com/example/auth/AuthRepository.kt
-index aaa..bbb 100644
---- a/app/src/main/java/com/example/auth/AuthRepository.kt
-+++ b/app/src/main/java/com/example/auth/AuthRepository.kt
-@@ -10,0 +11,12 @@ class AuthRepository @Inject constructor(
-+    open fun login(username: String, password: String): Result<Token> {
-+        if (username.isBlank() || password.isBlank()) return Result.failure(IllegalArgumentException())
-+        return try {
-+            val response = api.login(username, password)
-+            if (response.isSuccessful) Result.success(response.body()!!)
-+            else Result.failure(HttpException(response))
-+        } catch (e: IOException) {
-+            Result.failure(e)
-+        }
-+    }
-+
-+    open fun logout() { tokenStore.clear() }
-diff --git a/app/src/main/java/com/example/ui/HomeScreen.kt b/app/src/main/java/com/example/ui/HomeScreen.kt
-index ccc..ddd 100644
---- a/app/src/main/java/com/example/ui/HomeScreen.kt
-+++ b/app/src/main/java/com/example/ui/HomeScreen.kt
-@@ -20,0 +21,4 @@ fun HomeScreen(viewModel: HomeViewModel) {
-+    @Composable fun ItemRow(item: Item) {
-+        Text(item.title, modifier = Modifier.padding(8.dp))
-+    }
-+
-diff --git a/app/src/main/java/com/example/db/migrations/Migration_3_to_4.kt b/app/src/main/java/com/example/db/migrations/Migration_3_to_4.kt
-new file mode 100644
-index 000..eee
---- /dev/null
-+++ b/app/src/main/java/com/example/db/migrations/Migration_3_to_4.kt
-@@ -0,0 +1,8 @@
-+val MIGRATION_3_TO_4 = object : Migration(3, 4) {
-+    override fun migrate(database: SupportSQLiteDatabase) {
-+        database.execSQL("ALTER TABLE user ADD COLUMN created_at INTEGER NOT NULL DEFAULT 0")
-+        if (database.version < 4) {
-+            database.execSQL("CREATE INDEX idx_user_created ON user(created_at)")
-+        }
-+    }
-+}

package/pipeline/scripts/fixtures/diff-risk-ios.diff

@@ -1,48 +0,0 @@
-diff --git a/MyApp/Sources/Auth/KeychainStore.swift b/MyApp/Sources/Auth/KeychainStore.swift
-index 1111111..2222222 100644
---- a/MyApp/Sources/Auth/KeychainStore.swift
-+++ b/MyApp/Sources/Auth/KeychainStore.swift
-@@ -10,0 +11,18 @@ public final class KeychainStore {
-+    public func save(token: String, account: String) throws {
-+        guard !token.isEmpty else { throw KeychainError.emptyToken }
-+        let query: [String: Any] = [
-+            kSecClass as String: kSecClassGenericPassword,
-+            kSecAttrAccount as String: account,
-+            kSecValueData as String: Data(token.utf8)
-+        ]
-+        let status = SecItemAdd(query as CFDictionary, nil)
-+        if status == errSecDuplicateItem {
-+            let attrs: [String: Any] = [kSecValueData as String: Data(token.utf8)]
-+            let updateStatus = SecItemUpdate(query as CFDictionary, attrs as CFDictionary)
-+            guard updateStatus == errSecSuccess else { throw KeychainError.update(updateStatus) }
-+        } else if status != errSecSuccess {
-+            throw KeychainError.add(status)
-+        }
-+    }
-+
-+    public func load(account: String) throws -> String { /* impl */ }
-diff --git a/MyApp/Sources/Views/SettingsView.swift b/MyApp/Sources/Views/SettingsView.swift
-index 3333333..4444444 100644
---- a/MyApp/Sources/Views/SettingsView.swift
-+++ b/MyApp/Sources/Views/SettingsView.swift
-@@ -42,0 +43,3 @@ struct SettingsView: View {
-+            Text("Hello")
-+                .padding()
-+                .foregroundColor(.secondary)
-diff --git a/MyApp/Sources/Networking/ApiClient.swift b/MyApp/Sources/Networking/ApiClient.swift
-index 5555555..6666666 100644
---- a/MyApp/Sources/Networking/ApiClient.swift
-+++ b/MyApp/Sources/Networking/ApiClient.swift
-@@ -22,0 +23,5 @@ public class ApiClient {
-+    public func fetch<T: Decodable>(_ url: URL) async throws -> T {
-+        let (data, _) = try await URLSession.shared.data(from: url)
-+        if data.isEmpty { throw ApiError.empty }
-+        return try JSONDecoder().decode(T.self, from: data)
-+    }
-diff --git a/MyAppTests/SettingsViewTests.swift b/MyAppTests/SettingsViewTests.swift
-index 7777777..8888888 100644
---- a/MyAppTests/SettingsViewTests.swift
-+++ b/MyAppTests/SettingsViewTests.swift
-@@ -10,0 +11,2 @@ final class SettingsViewTests: XCTestCase {
-+    func testRenders() throws { /* impl */ }
-+

package/pipeline/scripts/fixtures/diff-risk-test-removal.diff

@@ -1,40 +0,0 @@
-diff --git a/MyAppTests/LoginViewModelTests.swift b/MyAppTests/LoginViewModelTests.swift
-index 1111111..2222222 100644
---- a/MyAppTests/LoginViewModelTests.swift
-+++ b/MyAppTests/LoginViewModelTests.swift
-@@ -10,30 +10,20 @@ final class LoginViewModelTests: XCTestCase {
-     func testLoginWithValidCredentials_Succeeds() {
-         let sut = LoginViewModel(service: MockAuthService())
-+        sut.retryPolicy = .none
-         sut.login(email: "user@example.com", password: "correct")
-+        XCTAssertTrue(sut.isAuthenticated)
-     }
--
--    func testLoginWithInvalidEmail_ShowsError() {
--        let sut = LoginViewModel(service: MockAuthService())
--        sut.login(email: "not-an-email", password: "irrelevant")
--        XCTAssertEqual(sut.errorMessage, "Invalid email")
--    }
--
--    func testLoginWithExpiredToken_Rejects() {
--        let sut = LoginViewModel(service: MockAuthService(tokenState: .expired))
--        sut.login(email: "user@example.com", password: "correct")
--        XCTAssertFalse(sut.isAuthenticated)
--    }
--
--    func testLogout_ClearsSession() {
--        let sut = LoginViewModel(service: MockAuthService())
--        sut.logout()
--        XCTAssertNil(sut.session)
--    }
- }
-diff --git a/MyApp/Sources/Auth/LoginViewModel.swift b/MyApp/Sources/Auth/LoginViewModel.swift
-index 3333333..4444444 100644
---- a/MyApp/Sources/Auth/LoginViewModel.swift
-+++ b/MyApp/Sources/Auth/LoginViewModel.swift
-@@ -20,6 +20,8 @@ final class LoginViewModel {
-     func login(email: String, password: String) {
-+        guard email.contains("@") else { return }
-+        service.authenticate(email: email, password: password)
-     }
- }

package/pipeline/scripts/fixtures/install-layout.tsv

@@ -1,19 +0,0 @@
-.claude/.pipeline-version	1
-.claude/CLAUDE.md	1
-.claude/agents	8
-.claude/commands	48
-.claude/lib	27
-.claude/multi-agent-preferences.json	1
-.claude/multi-agent-refs	52
-.claude/rules	12
-.claude/schemas	25
-.claude/scripts	201
-.claude/settings.json	1
-.claude/skills	428
-.copilot/.pipeline-version	1
-.copilot/agents	8
-.copilot/copilot-instructions.md	1
-.copilot/lib	27
-.copilot/schemas	25
-.copilot/scripts	201
-.copilot/skills	471

package/pipeline/scripts/fixtures/pack-expected-count.txt

@@ -1 +0,0 @@
-943

package/pipeline/scripts/fixtures/test-gap-node.diff

@@ -1,30 +0,0 @@
-diff --git a/src/lib/parser.ts b/src/lib/parser.ts
-index aaaa..bbbb 100644
---- a/src/lib/parser.ts
-+++ b/src/lib/parser.ts
-@@ -10,0 +11,8 @@
-+export function tokenize(input: string): string[] {
-+  return input.split(/\s+/);
-+}
-+
-+export class Parser {
-+  parse(tokens: string[]): unknown { return tokens; }
-+}
-+
-diff --git a/src/lib/format.ts b/src/lib/format.ts
-index cccc..dddd 100644
---- a/src/lib/format.ts
-+++ b/src/lib/format.ts
-@@ -5,0 +6,2 @@
-+export const formatNumber = (n: number): string => n.toFixed(2);
-+
-diff --git a/src/lib/__tests__/parser.test.ts b/src/lib/__tests__/parser.test.ts
-new file mode 100644
-index 000..eeee
---- /dev/null
-+++ b/src/lib/__tests__/parser.test.ts
-@@ -0,0 +1,4 @@
-+import { tokenize } from "../parser";
-+test("tokenize splits whitespace", () => {
-+  expect(tokenize("a b c")).toEqual(["a","b","c"]);
-+});

package/pipeline/scripts/fixtures/test-gap-python.diff

@@ -1,32 +0,0 @@
-diff --git a/src/payments/processor.py b/src/payments/processor.py
-index 1111..2222 100644
---- a/src/payments/processor.py
-+++ b/src/payments/processor.py
-@@ -10,0 +11,8 @@ class Processor:
-+    def charge(self, amount, currency):
-+        if amount <= 0:
-+            raise ValueError("amount must be positive")
-+        return self._gateway.charge(amount, currency)
-+
-+async def refund(transaction_id):
-+    return await api.refund(transaction_id)
-+
-diff --git a/src/payments/utils.py b/src/payments/utils.py
-index 3333..4444 100644
---- a/src/payments/utils.py
-+++ b/src/payments/utils.py
-@@ -5,0 +6,3 @@
-+def normalize_currency(code):
-+    return code.upper().strip()
-+
-diff --git a/tests/test_processor.py b/tests/test_processor.py
-new file mode 100644
-index 000..5555
---- /dev/null
-+++ b/tests/test_processor.py
-@@ -0,0 +1,5 @@
-+import pytest
-+
-+def test_charge_positive_amount():
-+    p = Processor()
-+    assert p.charge(10, "USD") is not None