Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

next
ts 155 lines 4.89 KB
Raw
1 import { describe, expect, test } from 'bun:test';
2 import {
3 countMarkdownTools,
4 cacheEntryBytes,
5 CACHE_ENTRY_LIMIT,
6 findInstantProblems,
7 findProblems,
8 PAGE_BYTES_BUDGET,
9 productionToolCounts,
10 selectWatchList,
11 } from '../../scripts/check-toolkit-parity';
12
13 const markdown = [
14 '# Tableau',
15 '',
16 '- **Tools:** 436',
17 '',
18 '## Frequently Asked Questions',
19 '',
20 '### Does it support OAuth?',
21 '',
22 '## Tools',
23 '',
24 '### List Users',
25 '',
26 '**Slug:** `TABLEAU_LIST_USERS`',
27 '',
28 '## Pagination',
29 '',
30 'Use the cursor to retrieve more users.',
31 '',
32 '### List Views',
33 '',
34 '**Slug:** `TABLEAU_LIST_VIEWS`',
35 '',
36 '## Triggers',
37 '',
38 '### New View',
39 '',
40 '**Slug:** `TABLEAU_NEW_VIEW_TRIGGER`',
41 ].join('\n');
42
43 const healthy = {
44 slug: 'tableau',
45 snapshotCount: 436,
46 productionCount: 436,
47 deployedCount: 436,
48 largestPageBytes: 1_231_773,
49 };
50
51 describe('countMarkdownTools', () => {
52 test('counts tools after a heading in a description and excludes triggers', () => {
53 expect(countMarkdownTools(markdown)).toBe(2);
54 });
55
56 test('returns 0 for a page without a Tools section', () => {
57 expect(countMarkdownTools('# Empty toolkit\n\n## Triggers\n\n**Slug:** `X`')).toBe(0);
58 });
59 });
60
61 describe('findProblems', () => {
62 test('accepts a page that matches production and the snapshot', () => {
63 expect(findProblems(healthy)).toEqual([]);
64 });
65
66 test('flags the stale tableau.md listing 10 of 436 tools', () => {
67 expect(findProblems({ ...healthy, deployedCount: 10 })).toEqual([
68 'tableau.md lists 10 tools; production has 436, the snapshot has 436',
69 ]);
70 });
71
72 test('accepts a page that still matches a snapshot awaiting its data-sync PR', () => {
73 expect(findProblems({ ...healthy, snapshotCount: 10, deployedCount: 10 })).toEqual([]);
74 });
75
76 test('flags a snapshot cut off at the API page cap', () => {
77 expect(findProblems({ ...healthy, slug: 'microsoft_365', snapshotCount: 1000, productionCount: 1208, deployedCount: 1208 })).toEqual([
78 'the microsoft_365 snapshot stops at 1000 of 1208 tools, the API page cap; the committed snapshot predates the paginated generator, so re-run generate:toolkits',
79 ]);
80 });
81
82 test('measures the page budget on the base64 cache entry, not the raw body', () => {
83 // 1.6 MB raw stays under 2 MiB, but its base64 entry (2.13 MB) does not fit.
84 expect(cacheEntryBytes(1_600_000)).toBeGreaterThan(CACHE_ENTRY_LIMIT);
85 expect(findProblems({ ...healthy, largestPageBytes: 1_600_000 })).toHaveLength(1);
86 expect(cacheEntryBytes(healthy.largestPageBytes)).toBeLessThanOrEqual(PAGE_BYTES_BUDGET);
87 });
88 });
89
90 describe('findInstantProblems', () => {
91 const instant = { productionSlugs: ['exa', 'tavily'], deployedSlugs: ['tavily', 'exa'], largestPageBytes: 400_000 };
92
93 test('accepts the same slugs in any order', () => {
94 expect(findInstantProblems(instant)).toEqual([]);
95 });
96
97 test('flags a deployed list frozen before a toolkit gained Instant support', () => {
98 expect(findInstantProblems({ ...instant, deployedSlugs: ['exa'] })).toEqual([
99 '/api/toolkits/instant lists 1 toolkits; production has 2 (missing: tavily; extra: none)',
100 ]);
101 });
102
103 test('flags a production /toolkits page whose cache entry is over budget', () => {
104 expect(findInstantProblems({ ...instant, largestPageBytes: 1_600_000 })).toHaveLength(1);
105 });
106 });
107
108 describe('selectWatchList', () => {
109 const snapshot = [
110 { slug: 'github', toolCount: 905 },
111 { slug: 'tableau', toolCount: 10 },
112 { slug: 'gmail', toolCount: 60 },
113 { slug: 'slack', toolCount: 150 },
114 ];
115
116 test('keeps a toolkit whose snapshot count collapsed, using production counts', () => {
117 const production = [
118 { slug: 'github', toolCount: 905 },
119 { slug: 'tableau', toolCount: 436 },
120 { slug: 'gmail', toolCount: 60 },
121 { slug: 'slack', toolCount: 150 },
122 ];
123
124 expect(selectWatchList(snapshot, production, 2).map(toolkit => toolkit.slug)).toEqual([
125 'github',
126 'tableau',
127 'slack',
128 ]);
129 });
130
131 test('carries snapshot counts and skips production toolkits without a published page', () => {
132 const production = [{ slug: 'unpublished', toolCount: 5000 }, { slug: 'tableau', toolCount: 436 }];
133
134 expect(selectWatchList(snapshot, production, 1)).toEqual([
135 { slug: 'tableau', toolCount: 10 },
136 { slug: 'github', toolCount: 905 },
137 ]);
138 });
139
140 test('falls back to the snapshot ranking without production counts', () => {
141 expect(selectWatchList(snapshot, [], 2).map(toolkit => toolkit.slug)).toEqual(['github', 'slack']);
142 });
143 });
144
145 describe('productionToolCounts', () => {
146 test('reads meta.tools_count and lowercases slugs', () => {
147 expect(productionToolCounts([{ slug: 'TABLEAU', meta: { tools_count: 436 } }])).toEqual([
148 { slug: 'tableau', toolCount: 436 },
149 ]);
150 });
151
152 test('rejects a listing without tool counts', () => {
153 expect(() => productionToolCounts([{ slug: 'tableau' }])).toThrow();
154 });
155 });