Blame · Line-by-line history

`index-existing-repo.test.ts`

Each line is annotated with the commit that last touched it. Click any SHA to jump to that commit and see the surrounding change.

index-existing-repo.test.tsBlame161 lines · 1 contributor

Normal view Raw

5d13cf5ccantynz-alt	1	/**
	2	* Repositories that arrive without a push must still be indexed.
	3	*
	4	* indexChangedFiles() is called from exactly ONE place — the git post-receive
	5	* hook. That is correct for pushes and wrong for every other way a repository
	6	* comes into existence:
	7	*
	8	* - bulk import CLONES (git clone fires no post-receive hook)
	9	* - POST /new + first-repo-scaffold writes via the git plumbing API
	10	* - forks copy the bare repo directly
	11	*
	12	* So both onboarding paths built in this session produced repositories where
	13	* gluecron_semantic_search, repo chat and "ask this repo" returned nothing.
	14	* Silently — an empty index is indistinguishable from "no matches", which is
	15	* why it survived. It was found while wiring the agent-first path, which
	16	* depends entirely on that index being populated.
	17	*
	18	* Deps are injected rather than mock.module()'d: ../git/repository is imported
	19	* by dozens of test files and a module mock leaks across the whole run.
	20	*/
	21
	22	import { describe, expect, it } from "bun:test";
	23	import { readFileSync } from "fs";
	24
	25	const SRC = readFileSync("src/lib/index-existing-repo.ts", "utf8");
	26
	27	type Entry = { name: string; type: string; path?: string };
	28
	29	function treeFrom(map: Record<string, Entry[]>) {
	30	return async (_o: string, _r: string, _ref: string, path?: string) =>
	31	map[path ?? ""] ?? [];
	32	}
	33
	34	describe("tree walking", () => {
	35	it("collects blobs across nested directories", async () => {
	36	const captured: string[][] = [];
	37	const { indexExistingRepo } = await import("../lib/index-existing-repo");
	38	const r = await indexExistingRepo(
	39	{ repositoryId: "r1", owner: "a", repoName: "b", ref: "main", commitSha: "sha" },
	40	{
	41	getTree: treeFrom({
	42	"": [
	43	{ name: "index.ts", type: "blob", path: "index.ts" },
	44	{ name: "src", type: "tree", path: "src" },
	45	],
	46	src: [{ name: "app.ts", type: "blob", path: "src/app.ts" }],
	47	}),
	48	indexChangedFiles: async (a) => {
	49	captured.push(a.changedPaths);
	50	return { indexed: a.changedPaths.length, skipped: 0, model: "test" };
	51	},
	52	}
	53	);
	54	expect(r.indexed).toBe(2);
	55	expect(captured[0].sort()).toEqual(["index.ts", "src/app.ts"]);
	56	});
	57
	58	it("skips vendor and build directories", async () => {
	59	let seen: string[] = [];
	60	const { indexExistingRepo } = await import("../lib/index-existing-repo");
	61	await indexExistingRepo(
	62	{ repositoryId: "r1", owner: "a", repoName: "b", ref: "main", commitSha: "sha" },
	63	{
	64	getTree: treeFrom({
	65	"": [
	66	{ name: "node_modules", type: "tree", path: "node_modules" },
	67	{ name: "dist", type: "tree", path: "dist" },
	68	{ name: "keep.ts", type: "blob", path: "keep.ts" },
	69	],
	70	node_modules: [{ name: "junk.js", type: "blob", path: "node_modules/junk.js" }],
	71	dist: [{ name: "out.js", type: "blob", path: "dist/out.js" }],
	72	}),
	73	indexChangedFiles: async (a) => {
	74	seen = a.changedPaths;
	75	return { indexed: a.changedPaths.length, skipped: 0, model: "test" };
	76	},
	77	}
	78	);
	79	expect(seen).toEqual(["keep.ts"]);
	80	});
	81
	82	it("delegates filtering to indexChangedFiles rather than duplicating it", () => {
	83	// isCodeFile, the per-push cap and the embedding model all live in
	84	// semantic-index.ts. Re-implementing them here would let scaffolded and
	85	// pushed repos drift apart in what they index.
	86	//
	87	// Comments stripped: the source explains this delegation in prose that
	88	// names the very symbol being asserted absent.
	89	const code = SRC.replace(/\/\[\s\S]?\\//g, "").replace(/^\s\/\/.*$/gm, "");
	90	expect(code).toContain("indexChangedFiles");
	91	expect(code).not.toContain("isCodeFile");
	92	});
	93	});
	94
	95	describe("fault isolation", () => {
	96	it("never throws when the tree read fails", async () => {
	97	const { indexExistingRepo } = await import("../lib/index-existing-repo");
	98	const r = await indexExistingRepo(
	99	{ repositoryId: "r1", owner: "a", repoName: "b", ref: "main", commitSha: "sha" },
	100	{
	101	getTree: async () => {
	102	throw new Error("disk on fire");
	103	},
	104	indexChangedFiles: async () => ({ indexed: 0, skipped: 0, model: "test" }),
	105	}
	106	);
	107	// A single unreadable directory must not abandon the index, and an
	108	// unindexed repo must never fail an import or a repo creation.
	109	expect(r.indexed).toBe(0);
	110	expect(r.error).toBeUndefined();
	111	});
	112
	113	it("reports an embedding failure instead of throwing", async () => {
	114	const { indexExistingRepo } = await import("../lib/index-existing-repo");
	115	const r = await indexExistingRepo(
	116	{ repositoryId: "r1", owner: "a", repoName: "b", ref: "main", commitSha: "sha" },
	117	{
	118	getTree: treeFrom({ "": [{ name: "a.ts", type: "blob", path: "a.ts" }] }),
	119	indexChangedFiles: async () => {
	120	throw new Error("embedder down");
	121	},
	122	}
	123	);
	124	expect(r.indexed).toBe(0);
	125	expect(r.error).toContain("embedder down");
	126	});
	127
	128	it("returns zero for an empty repository without calling the embedder", async () => {
	129	let called = false;
	130	const { indexExistingRepo } = await import("../lib/index-existing-repo");
	131	const r = await indexExistingRepo(
	132	{ repositoryId: "r1", owner: "a", repoName: "b", ref: "main", commitSha: "sha" },
	133	{
	134	getTree: treeFrom({}),
	135	indexChangedFiles: async () => {
	136	called = true;
	137	return { indexed: 0, skipped: 0, model: "test" };
	138	},
	139	}
	140	);
	141	expect(r.indexed).toBe(0);
	142	expect(called).toBe(false);
	143	});
	144	});
	145
	146	describe("both onboarding paths index", () => {
	147	it("bulk import indexes each repo", () => {
	148	const mig = readFileSync("src/lib/migration-onboarding.ts", "utf8");
	149	expect(mig).toContain("indexExistingRepo");
	150	expect(mig).toContain("filesIndexed");
	151	});
	152
	153	it("new-repo scaffold indexes after committing", () => {
	154	const scaffold = readFileSync("src/lib/first-repo-scaffold.ts", "utf8");
	155	expect(scaffold).toContain("indexExistingRepo");
	156	// Must come after the commits — there is nothing to index before them.
	157	expect(scaffold.indexOf("createOrUpdateFileOnBranch")).toBeLessThan(
	158	scaffold.lastIndexOf("indexExistingRepo")
	159	);
	160	});
	161	});