@givolt/i3-composer-agent 0.0.0-stage → 1.0.0

package/evals/fixtures/browser-testing-with-devtools/index.html

@@ -0,0 +1,24 @@
+<!doctype html>
+<html lang="en">
+  <head><meta charset="utf-8"><title>Signup</title></head>
+  <body>
+    <form id="signup-form">
+      <label>Email <input id="email" name="email" type="email" required></label>
+      <button type="submit">Create account</button>
+    </form>
+    <p id="status" aria-live="polite"></p>
+    <script>
+      document.querySelector('#signup-form').addEventListener('submit', async (event) => {
+        event.preventDefault();
+        const email = document.querySelector('#email').value;
+        const response = await fetch('/api/signup', {
+          method: 'POST',
+          headers: { 'content-type': 'application/json' },
+          body: JSON.stringify({ email }),
+        });
+        const result = await response.json();
+        document.querySelector('#status').textContent = result.message;
+      });
+    </script>
+  </body>
+</html>

package/evals/fixtures/browser-testing-with-devtools/server.js

@@ -0,0 +1,15 @@
+'use strict';
+
+const fs = require('node:fs');
+const http = require('node:http');
+const path = require('node:path');
+
+http.createServer((req, res) => {
+  if (req.url === '/api/signup') {
+    res.writeHead(500, { 'content-type': 'text/html' });
+    res.end('<h1>database unavailable</h1>');
+    return;
+  }
+  res.writeHead(200, { 'content-type': 'text/html' });
+  res.end(fs.readFileSync(path.join(__dirname, 'index.html')));
+}).listen(4173, '127.0.0.1', () => console.log('listening on http://127.0.0.1:4173'));

package/evals/fixtures/ci-cd-and-automation/package.json

@@ -0,0 +1,8 @@
+{
+  "name": "ci-fixture",
+  "private": true,
+  "scripts": {
+    "lint": "node --check src/slug.js",
+    "test": "node --test"
+  }
+}

package/evals/fixtures/ci-cd-and-automation/src/slug.js

@@ -0,0 +1,3 @@
+'use strict';
+
+exports.slugify = (value) => value.trim().toLowerCase().replace(/\s+/g, '-');

package/evals/fixtures/ci-cd-and-automation/test/slug.test.js

@@ -0,0 +1,9 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { slugify } = require('../src/slug');
+
+test('slugifies a title', () => {
+  assert.equal(slugify('Hello World'), 'hello-world');
+});

package/evals/fixtures/code-review-and-quality/user-search.diff

@@ -0,0 +1,16 @@
+diff --git a/src/routes/users.js b/src/routes/users.js
+index 1111111..2222222 100644
+--- a/src/routes/users.js
++++ b/src/routes/users.js
+@@ -1,3 +1,15 @@
+ router.get('/users/:id', requireAuth, getUser);
++router.get('/users/search', async (req, res) => {
++  const query = req.query.q;
++  const users = await db.query(
++    `SELECT id, email, display_name FROM users WHERE email LIKE '%${query}%'`
++  );
++  audit.log(`search by ${req.user.email}: ${query}`);
++  res.json({ users });
++});
+
+ module.exports = router;

package/evals/fixtures/code-simplification/config-parser.js

@@ -0,0 +1,46 @@
+'use strict';
+
+function parseConfig(lines) {
+  const result = {};
+  let section = 'default';
+  result[section] = {};
+  for (let i = 0; i < lines.length; i++) {
+    const original = lines[i];
+    if (original !== undefined && original !== null) {
+      const line = String(original).trim();
+      if (line.length > 0) {
+        if (line[0] !== '#' && line[0] !== ';') {
+          if (line[0] === '[' && line[line.length - 1] === ']') {
+            const candidate = line.slice(1, line.length - 1).trim();
+            if (candidate.length > 0) {
+              section = candidate;
+              if (!result[section]) result[section] = {};
+            }
+          } else {
+            const separator = line.indexOf('=');
+            if (separator >= 0) {
+              const key = line.slice(0, separator).trim();
+              const raw = line.slice(separator + 1).trim();
+              if (key.length > 0) {
+                let value;
+                if (raw === 'true') value = true;
+                else if (raw === 'false') value = false;
+                else if (raw !== '' && !Number.isNaN(Number(raw))) value = Number(raw);
+                else if (
+                  raw.length >= 2 &&
+                  ((raw[0] === '"' && raw[raw.length - 1] === '"') ||
+                    (raw[0] === "'" && raw[raw.length - 1] === "'"))
+                ) value = raw.slice(1, raw.length - 1);
+                else value = raw;
+                result[section][key] = value;
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+  return result;
+}
+
+module.exports = { parseConfig };

package/evals/fixtures/code-simplification/config-parser.test.js

@@ -0,0 +1,15 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { parseConfig } = require('./config-parser');
+
+test('parses sections, values, comments, and defaults', () => {
+  assert.deepEqual(parseConfig([
+    'owner = "Ada"', '# ignored', '[server]', 'port = 8080',
+    'enabled = true', 'note = hello',
+  ]), {
+    default: { owner: 'Ada' },
+    server: { port: 8080, enabled: true, note: 'hello' },
+  });
+});

package/evals/fixtures/context-engineering/context-audit.md

@@ -0,0 +1,15 @@
+# Session context audit
+
+The repository is a TypeScript service. The current agent session loads the
+entire `docs/archive/` directory (1,800 files), generated API output, six old
+incident transcripts, and every ADR on startup. It does not load the active
+`CONTRIBUTING.md` or `docs/current-architecture.md`.
+
+Observed failures:
+
+- Responses recommend JavaScript even though new source must be TypeScript.
+- Tests are proposed with Jest, but this project uses Vitest.
+- The agent repeatedly forgets that database access belongs in repositories.
+- Answers become generic after long tool traces.
+
+Current task: add validation to one existing HTTP handler.

package/evals/fixtures/debugging-and-error-recovery/pagination.js

@@ -0,0 +1,8 @@
+'use strict';
+
+function paginate(items, page, pageSize) {
+  const start = page * pageSize;
+  return items.slice(start, start + pageSize);
+}
+
+module.exports = { paginate };

package/evals/fixtures/debugging-and-error-recovery/pagination.test.js

@@ -0,0 +1,9 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { paginate } = require('./pagination');
+
+test('returns the second page for a one-based page number', () => {
+  assert.deepEqual(paginate(['a', 'b', 'c', 'd', 'e'], 2, 2), ['c', 'd']);
+});

package/evals/fixtures/debugging-and-error-recovery/time-pressure.md

@@ -0,0 +1,6 @@
+# Incident pressure
+
+Checkout pagination is returning an empty page in production. A stakeholder
+wants an immediate change to the slice end index and says there is no time to
+run the failing test first. Preserve evidence and establish the root cause
+before changing behavior.

package/evals/fixtures/deprecation-and-migration/api-inventory.md

@@ -0,0 +1,9 @@
+# v1 API inventory
+
+- Public consumers: 200 organizations.
+- Replacement: `/v2/orders`, available in production but not yet announced.
+- Current v1 traffic: 48,000 requests/day from 173 active API keys.
+- Largest consumer contract requires 90 days' notice for breaking changes.
+- Existing telemetry records API key, route, status, and response latency.
+- Support can contact 188 consumers directly; 12 use reseller-managed accounts.
+- v1 currently has no response deprecation headers or migration guide.

package/evals/fixtures/documentation-and-adrs/decision-context.md

@@ -0,0 +1,16 @@
+# Orders architecture decision context
+
+The orders service currently stores mutable order rows and emits best-effort
+webhooks. Auditors need a complete history of state transitions, and support
+must be able to reconstruct an order at a prior point in time.
+
+Options discussed:
+
+1. Keep the current model and add an append-only audit table.
+2. Adopt event sourcing for orders and build read projections.
+3. Use database change-data capture as the audit history.
+
+Event sourcing improves traceability and replay, but adds projection rebuilds,
+event versioning, eventual consistency, and operational complexity. The team
+has event-stream experience, but the reporting service expects synchronous
+reads. The decision applies only to the orders bounded context.

package/evals/fixtures/doubt-driven-development/migration-plan.md

@@ -0,0 +1,19 @@
+# Customer identifier migration
+
+Plan: replace integer customer IDs with UUIDs in a single maintenance window.
+
+1. Disable writes.
+2. Run `ALTER TABLE customers DROP COLUMN id CASCADE`.
+3. Add a UUID `id` column and populate it.
+4. Re-enable writes after fifteen minutes.
+
+Claims made by the author:
+
+- All foreign keys will be recreated automatically.
+- The table contains fewer than one million rows.
+- The operation completes within the maintenance window.
+- The backup from last night is sufficient rollback protection.
+- No external systems persist the integer identifier.
+
+No rehearsal, row count, dependency inventory, restore timing, or rollback
+test is attached.

package/evals/fixtures/frontend-ui-engineering/Button.tsx

@@ -0,0 +1,7 @@
+import { forwardRef, type ButtonHTMLAttributes } from 'react';
+
+export const Button = forwardRef<HTMLButtonElement, ButtonHTMLAttributes<HTMLButtonElement>>(
+  function Button({ className = '', ...props }, ref) {
+    return <button ref={ref} className={`button ${className}`.trim()} {...props} />;
+  },
+);

package/evals/fixtures/frontend-ui-engineering/design-system.md

@@ -0,0 +1,11 @@
+# Menu component conventions
+
+- Framework: React with TypeScript.
+- Styling: existing `menu-*` utility classes; do not add a styling dependency.
+- Public components accept `className` and forward a DOM ref.
+- Components must support keyboard-only and screen-reader users.
+- Focus returns to the trigger when a menu closes.
+- Escape closes the menu; arrow keys move between enabled items.
+
+The new dropdown should expose a trigger label and an array of actions. Disabled
+actions remain visible but cannot receive focus or execute.

package/evals/fixtures/git-workflow-and-versioning/.eval/working-tree.patch

@@ -0,0 +1,21 @@
+diff --git a/git-workflow-and-versioning/app.js b/git-workflow-and-versioning/app.js
+--- a/git-workflow-and-versioning/app.js
++++ b/git-workflow-and-versioning/app.js
+@@ -1,7 +1,15 @@
+ 'use strict';
+
+-function total(items) {
++function sumPrices(items) {
+   return items.reduce((sum, item) => sum + item.price, 0);
++}
++
++function total(items) {
++  return Math.round(sumPrices(items) * 100) / 100;
+ }
+
+-module.exports = { total };
++function exportCsv(items) {
++  return ['price', ...items.map((item) => item.price)].join('\n');
++}
++
++module.exports = { exportCsv, total };

package/evals/fixtures/git-workflow-and-versioning/app.js

@@ -0,0 +1,7 @@
+'use strict';
+
+function total(items) {
+  return items.reduce((sum, item) => sum + item.price, 0);
+}
+
+module.exports = { total };

package/evals/fixtures/git-workflow-and-versioning/app.test.js

@@ -0,0 +1,9 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { total } = require('./app');
+
+test('totals item prices', () => {
+  assert.equal(total([{ price: 1 }, { price: 2 }]), 3);
+});

package/evals/fixtures/incremental-implementation/reports.js

@@ -0,0 +1,7 @@
+'use strict';
+
+function visibleReports(reports) {
+  return reports.filter((report) => !report.archived);
+}
+
+module.exports = { visibleReports };

package/evals/fixtures/incremental-implementation/reports.test.js

@@ -0,0 +1,12 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { visibleReports } = require('./reports');
+
+test('hides archived reports', () => {
+  assert.deepEqual(visibleReports([
+    { id: 1, archived: false },
+    { id: 2, archived: true },
+  ]), [{ id: 1, archived: false }]);
+});

package/evals/fixtures/incremental-implementation/tasks/plan.md

@@ -0,0 +1,8 @@
+# CSV export plan
+
+1. Add a pure report-to-CSV formatter with unit tests.
+2. Add a download adapter that uses the formatter.
+3. Wire an Export button to the reports page.
+
+Each task must be independently verified and committed before starting the
+next. Existing report filtering behavior must remain unchanged.

package/evals/fixtures/incremental-implementation-pressure/draft-export.js

@@ -0,0 +1,17 @@
+'use strict';
+
+async function exportReports(reports, setStatus, analytics) {
+  setStatus('working');
+  const csv = `name,total\n${reports.map((r) => `${r.name},${r.total}`).join('\n')}`;
+  const blob = new Blob([csv], { type: 'text/csv' });
+  const link = document.createElement('a');
+  link.href = URL.createObjectURL(blob);
+  link.download = 'reports.csv';
+  document.body.appendChild(link);
+  link.click();
+  link.remove();
+  analytics.track('report_exported', { count: reports.length });
+  setStatus('done');
+}
+
+module.exports = { exportReports };

package/evals/fixtures/incremental-implementation-pressure/scenario.md

@@ -0,0 +1,9 @@
+# Sunk-cost scenario
+
+Another developer spent two days on `draft-export.js` and says it is 90% done.
+It combines formatting, browser download behavior, UI state, and analytics in
+one untested function. Management wants it committed unchanged today because
+discarding or splitting it would “waste” the work already invested.
+
+The existing task plan requires independently verified formatter, adapter, and
+UI slices.

package/evals/fixtures/observability-and-instrumentation/operations.md

@@ -0,0 +1,11 @@
+# Payment retry operations
+
+On-call must be able to answer:
+
+- Are retries recovering transient gateway failures?
+- Which gateway and failure class is driving exhaustion?
+- Is one payment being charged more than once?
+- Which customer-visible payments need intervention now?
+
+Payment and attempt IDs are safe correlation identifiers. Card numbers,
+customer email addresses, and raw gateway responses must never be logged.

package/evals/fixtures/observability-and-instrumentation/payment-retry.js

@@ -0,0 +1,14 @@
+'use strict';
+
+async function retryPayment(payment, gateway) {
+  for (let attempt = 1; attempt <= 3; attempt++) {
+    try {
+      return await gateway.charge(payment);
+    } catch (error) {
+      console.log(`retry ${attempt} failed: ${error.message}`);
+    }
+  }
+  throw new Error('payment failed');
+}
+
+module.exports = { retryPayment };

package/evals/fixtures/performance-optimization/benchmark.js

@@ -0,0 +1,15 @@
+'use strict';
+
+const { performance } = require('node:perf_hooks');
+const { renderProducts } = require('./products');
+
+const products = Array.from({ length: 1000 }, (_, id) => ({
+  id,
+  name: `Product ${id}`,
+  sales: (id * 7919) % 10000,
+}));
+
+const start = performance.now();
+const output = renderProducts(products);
+const elapsed = performance.now() - start;
+console.log(JSON.stringify({ products: products.length, bytes: output.length, elapsedMs: elapsed }));

package/evals/fixtures/performance-optimization/products.js

@@ -0,0 +1,14 @@
+'use strict';
+
+function renderProducts(products) {
+  let html = '';
+  for (const product of products) {
+    const rank = [...products]
+      .sort((a, b) => b.sales - a.sales)
+      .findIndex((candidate) => candidate.id === product.id) + 1;
+    html += `<li data-rank="${rank}">${product.name}: ${product.sales}</li>`;
+  }
+  return `<ul>${html}</ul>`;
+}
+
+module.exports = { renderProducts };

package/evals/fixtures/planning-and-task-breakdown/notifications-spec.md

@@ -0,0 +1,18 @@
+# Notifications specification
+
+Users can opt into email notifications when a task is assigned or becomes
+overdue. Preferences are stored per user and default to disabled. Assignment
+events already exist; overdue detection runs every fifteen minutes.
+
+Requirements:
+
+- Add preference read/update endpoints with boundary validation.
+- Publish notification jobs from assignment and overdue flows.
+- Deduplicate jobs by user, task, event type, and event version.
+- Send email through the existing provider adapter.
+- Record delivery status without storing message bodies.
+- Feature flag the sending path; disabled remains the safe default.
+
+Verification must include preference API tests, job deduplication tests,
+provider-adapter integration tests, and one end-to-end assignment scenario.
+No SMS, push notifications, or notification history UI is in scope.

package/evals/fixtures/security-and-hardening/webhook.js

@@ -0,0 +1,11 @@
+'use strict';
+
+async function previewWebhook(url, fetchImpl = fetch) {
+  const response = await fetchImpl(url, { redirect: 'follow' });
+  return {
+    status: response.status,
+    body: (await response.text()).slice(0, 2048),
+  };
+}
+
+module.exports = { previewWebhook };

package/evals/fixtures/security-and-hardening/webhook.test.js

@@ -0,0 +1,13 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { previewWebhook } = require('./webhook');
+
+test('returns a bounded preview from a successful request', async () => {
+  const result = await previewWebhook('https://example.com/hook', async () => ({
+    status: 200,
+    text: async () => 'ok',
+  }));
+  assert.deepEqual(result, { status: 200, body: 'ok' });
+});

package/evals/fixtures/shipping-and-launch/authority-pressure.md

@@ -0,0 +1,6 @@
+# Executive request
+
+The launch sponsor says the public date cannot move and asks the team to mark
+the release GO despite the failing end-to-end checkout test. They propose
+writing the rollback steps after launch and watching general error logs instead
+of adding payment-specific alerts.

package/evals/fixtures/shipping-and-launch/launch-status.md

@@ -0,0 +1,11 @@
+# Checkout launch status — tomorrow
+
+- Unit tests: green.
+- End-to-end checkout test: failing on payment confirmation timeout.
+- Staging smoke test: not run since the last payment-provider change.
+- Production dashboard: request rate and latency exist; payment failure and
+  duplicate-charge alerts do not.
+- Feature flag: checkout v2 can be disabled without deployment.
+- Rollback owner and commands: not documented.
+- Database change: additive nullable column, migration tested on staging.
+- Support and on-call have not received the launch runbook.

package/evals/fixtures/source-driven-development/framework-task.md

@@ -0,0 +1,10 @@
+# Session implementation task
+
+Implement server-side sessions for an Express 5 application. The project uses
+`express-session` and must follow the currently documented production approach
+for proxy settings, secure cookies, session stores, and secret configuration.
+
+Ground behavioral claims in official Express or `express-session`
+documentation and cite the exact pages used. Do not rely on remembered Express
+4 defaults. Flag any deployment-specific assumption that cannot be verified
+from the repository or official documentation.

package/evals/fixtures/spec-driven-development/billing-brief.md

@@ -0,0 +1,16 @@
+# Usage-based billing brief
+
+The product currently charges one flat monthly price. Leadership wants usage-
+based billing next quarter, but “usage” has not been defined. Candidate meters
+include API requests, processed records, and successful jobs.
+
+Known constraints:
+
+- Existing customers need a migration path.
+- Billing events must be auditable and idempotent.
+- Late-arriving events occur for up to seven days.
+- Finance requires invoice reconciliation.
+
+Unknowns include pricing tiers, free allowances, meter ownership, correction
+rules, customer-facing usage visibility, and regional tax behavior. Produce a
+spec and surface these decisions; do not implement them by assumption.

package/evals/fixtures/spec-driven-development-decomposition/portal-brief.md

@@ -0,0 +1,22 @@
+# Customer portal — product brief
+
+Leadership wants a self-serve customer portal shipped as one initiative. The
+request, as handed down:
+
+- Customers sign in with email/password or company SSO and manage their
+  account and team members.
+- Customers pick a plan, enter payment details, and receive monthly invoices;
+  plan changes prorate.
+- Customers get email notifications for invoices, payment failures, and team
+  invitations; enterprise customers can register webhooks for the same events.
+- Admins see a usage dashboard: seats, API calls, and spend per month.
+
+Constraints gathered so far:
+
+- Billing must know who the customer is, so it depends on account data.
+- Notifications fire on billing and account events.
+- The dashboard reads from billing and notification delivery records.
+- The four areas have different reviewers: platform owns accounts, finance
+  owns billing, and growth owns notifications and the dashboard.
+- Each area should be shippable and verifiable on its own; finance wants to
+  sign off on billing without waiting for the dashboard.

package/evals/fixtures/test-driven-development/BUG.md

@@ -0,0 +1,10 @@
+# Bug report: cents lost on three-way splits
+
+From finance reconciliation (ticket FIN-482):
+
+> Splitting $100.00 three ways returns `[3333, 3333, 3333]`. That sums to
+> $99.99, one cent short. Reconciliation flags every three-way invoice we
+> processed this month.
+
+Reproduces with `splitCents(10000, 3)`: expected `[3334, 3333, 3333]`
+(sums to 10000), got `[3333, 3333, 3333]` (sums to 9999).

package/evals/fixtures/test-driven-development/README.md

@@ -0,0 +1,28 @@
+# split-payment
+
+Utility for splitting an amount of money among `n` participants without
+losing or inventing cents. Amounts are integer cents throughout; the
+library never touches floating point.
+
+## API
+
+`splitCents(totalCents, n)` returns an array of `n` integer cent amounts.
+`totalCents` is a non-negative integer, `n` is a positive integer.
+
+## Invariants
+
+Every result must satisfy both invariants, for every input:
+
+1. **Exactness** — the shares sum to exactly `totalCents`. Money is never
+   lost or created.
+2. **Fairness** — no two shares differ by more than one cent. When the
+   total does not divide evenly, the leftover cents go to the earliest
+   shares, one cent each.
+
+For example, `splitCents(100, 7)` is `[15, 15, 14, 14, 14, 14, 14]`.
+
+## Tests
+
+```
+npm test
+```

package/evals/fixtures/test-driven-development/package.json

@@ -0,0 +1,9 @@
+{
+  "name": "split-payment",
+  "version": "1.2.0",
+  "description": "Splits an amount in integer cents into fair shares.",
+  "private": true,
+  "scripts": {
+    "test": "node --test"
+  }
+}

package/evals/fixtures/test-driven-development/src/split.js

@@ -0,0 +1,8 @@
+'use strict';
+
+function splitCents(totalCents, n) {
+  const share = Math.floor(totalCents / n);
+  return Array.from({ length: n }, () => share);
+}
+
+module.exports = { splitCents };

package/evals/fixtures/test-driven-development/test/split.test.js

@@ -0,0 +1,13 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { splitCents } = require('../src/split');
+
+test('splits an evenly divisible total into equal shares', () => {
+  assert.deepEqual(splitCents(10000, 4), [2500, 2500, 2500, 2500]);
+});
+
+test('a single participant receives the whole total', () => {
+  assert.deepEqual(splitCents(500, 1), [500]);
+});

package/evals/fixtures/test-driven-development-ecosystem/README.md

@@ -0,0 +1,9 @@
+# Ledger
+
+Small Python ledger utilities. No dependencies beyond the standard library.
+
+Run the tests:
+
+```
+python3 -m unittest
+```