Files
Ekklesia/tests/ci-scripts.test.ts
T
ekklesiaandClaude Opus 5.5 278e66049f
CI / verify (pull_request) Successful in 50s
CI / infrastructure-smoke (pull_request) Successful in 14s
CI / migration-smoke (pull_request) Successful in 1m49s
CI / image-build (pull_request) Successful in 19s
CI / deploy-smoke (pull_request) Successful in 41s
fix(ci): isolate concurrent runs on a shared Docker daemon and explain readiness failures
PR #51's migration-smoke failed 0.7 s after the build: the suite pinned
PostgreSQL to an ephemeral port but inherited S3_PORT=8333 from
.env.example, so concurrent runs on one runner (Gitea ignores workflow
concurrency) contended for one host port. Compose's own error was
discarded, so the failure said only that the services "did not become
ready".

Isolation, from an audit of every script CI runs:
- test-migrations-integration.sh: S3_PORT=0, like POSTGRES_PORT=0.
- test-migrations-integration.sh and smoke-infrastructure.sh: project names
  gain a random suffix; run id plus PID alone is not unique when job
  containers share low PIDs.
- smoke-deploy.sh: the edge /24 is chosen from those no network on the
  daemon uses, and the first `up` chooses again when a concurrent run wins
  a race for the same subnet (Docker's address-pool overlap), up to five
  times.
- CI image-build: the image tag includes the run id and attempt, so a pull
  request and a push of the same commit cannot remove each other's image.
- Already isolated: every other published port (ephemeral), the TLS
  suite's container and network (random), smoke staging directories and
  image tags (random).

Diagnostics: scripts/lib/compose-diagnostics.sh prints the failed `up`
command's output, `docker compose ps`, and the last 40 log lines of each
service, all redacted (supplied literals, credential-looking NAME=value
pairs, URL user information, Authorization headers) with terminal control
sequences stripped. All three scripts use it at every readiness check; the
infrastructure smoke's unredacted full-log dump is replaced by it.

tests/ci-scripts.test.ts pins ephemeral ports, unique project names, the
subnet choice, the CI image tag, the diagnostics, and the redaction itself
(run through bash).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-03 12:15:01 -05:00

166 lines
7.3 KiB
TypeScript

import { execFile } from "node:child_process";
import { readFile } from "node:fs/promises";
import path from "node:path";
import { fileURLToPath } from "node:url";
import { promisify } from "node:util";
import { describe, expect, it } from "vitest";
/**
* The scripts CI runs against a shared Docker daemon. Several runs, and several jobs of one run, can
* be active on one runner at once (and the inventoried Gitea ignores workflow `concurrency`), so
* nothing they start may claim a fixed host port, a fixed project or network name, or a fixed
* subnet. And when a disposable project does not become ready, the failure must say why without
* printing a credential.
*/
const repositoryRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
const execFileAsync = promisify(execFile);
const ciScripts = [
"scripts/test-migrations-integration.sh",
"scripts/smoke-infrastructure.sh",
"scripts/smoke-deploy.sh",
];
async function source(relativePath: string): Promise<string> {
return readFile(path.join(repositoryRoot, relativePath), "utf8");
}
/** Runs the real helper under bash with the given literal secrets and input. */
async function redact(input: string, secrets: readonly string[] = []): Promise<string> {
const helper = path.join(repositoryRoot, "scripts", "lib", "compose-diagnostics.sh");
const script = `source "$1"; shift; COMPOSE_DIAGNOSTICS_SECRETS=("$@"); printf '%s' "$INPUT" | compose_diagnostics_redact`;
const { stdout } = await execFileAsync("bash", ["-c", script, "redact", helper, ...secrets], {
env: { ...process.env, INPUT: input },
});
return stdout;
}
describe("CI scripts on a shared Docker daemon", () => {
it("publish every host port ephemerally, never a fixed one", async () => {
const migrations = await source("scripts/test-migrations-integration.sh");
// `.env.example` pins both ports for local development; the suite must override both.
expect(migrations).toContain('export POSTGRES_PORT="0"');
expect(migrations).toContain('export S3_PORT="0"');
const infrastructure = await source("scripts/smoke-infrastructure.sh");
expect(infrastructure).toContain('export POSTGRES_PORT="${EKKLESIA_SMOKE_POSTGRES_PORT:-0}"');
expect(infrastructure).toContain('export S3_PORT="${EKKLESIA_SMOKE_S3_PORT:-0}"');
const deploy = await source("scripts/smoke-deploy.sh");
expect(deploy).toContain("EKKLESIA_HTTP_PORT=0");
expect(deploy).toContain("EKKLESIA_HTTPS_PORT=0");
for (const relativePath of ciScripts) {
const text = await source(relativePath);
// No `-p 8333:…`, `127.0.0.1:5432:…`, or `PORT=<non-zero>` anywhere.
expect(text, relativePath).not.toMatch(/\b(?:-p|--publish)\s+[^\s]*\d{2,5}:\d/u);
expect(text, relativePath).not.toMatch(/\b[A-Z_]*PORT="?[1-9]\d*"?\s*$/mu);
}
});
it("give every Compose project a name unique to the invocation, not only the run", async () => {
expect(await source("scripts/test-migrations-integration.sh")).toMatch(
/raw_project="ekklesia-migration-[^"\n]*\$\$-\$\{RANDOM\}\$\{RANDOM\}"/u,
);
expect(await source("scripts/smoke-infrastructure.sh")).toMatch(
/raw_project="ekklesia-smoke-[^"\n]*\$\$-\$\{RANDOM\}\$\{RANDOM\}"/u,
);
const deploy = await source("scripts/smoke-deploy.sh");
expect(deploy).toContain('run_id="$(openssl rand -hex 4)"');
expect(deploy).toContain('project="ekklesia-deploy-smoke-${run_id}"');
for (const relativePath of ciScripts) {
expect(await source(relativePath), relativePath).toContain('--project-name "$project"');
}
});
it("choose the deploy smoke's edge subnet from those not in use, and choose again on a race", async () => {
const deploy = await source("scripts/smoke-deploy.sh");
expect(deploy).not.toMatch(/^octet=\$\(\(RANDOM/mu);
expect(deploy).toContain("choose_edge_network() {");
expect(deploy).toContain("docker network inspect --format '{{range .IPAM.Config}}");
expect(deploy).toContain('[[ "$up_output" == *"overlap"* ]]');
});
it("tag the CI image per run and attempt, so concurrent runs of one commit cannot remove it", async () => {
const workflow = await source(".github/workflows/ci.yml");
expect(workflow).toContain(
'ekklesia-ci:"$GITHUB_SHA-${GITHUB_RUN_ID:-0}-${GITHUB_RUN_ATTEMPT:-1}"',
);
expect(workflow).not.toContain('ekklesia-ci:"$GITHUB_SHA"');
});
it("report every readiness failure with the project's containers and logs, through the redactor only", async () => {
for (const relativePath of ciScripts) {
const text = await source(relativePath);
expect(text, relativePath).toContain(
'source "$repository_root/scripts/lib/compose-diagnostics.sh"',
);
expect(text, relativePath).toContain("compose_report_not_ready");
expect(text, relativePath).toContain("COMPOSE_DIAGNOSTICS_SECRETS=(");
// Compose output is never printed raw: logs are only ever captured (the deploy smoke scans
// the API's for secrets), and a readiness failure's own output is never discarded.
for (const line of text
.split("\n")
.filter((candidate) => candidate.includes('compose[@]}" logs'))) {
expect(line, relativePath).toMatch(/="\$\("\$\{compose\[@\]\}" logs /u);
}
expect(text, relativePath).not.toMatch(/up --detach --wait[^\n]*>\/dev\/null 2>&1/u);
}
});
});
describe("compose diagnostics redaction", () => {
it("masks credential-looking values, URL user information, and Authorization headers", async () => {
const output = await redact(
[
"POSTGRES_PASSWORD=hunter2hunter2",
' "AWS_SECRET_ACCESS_KEY": "abc/def+ghi"',
"S3_ACCESS_KEY=AKIAEXAMPLE other=fine",
"api_key: xyz123",
"connecting to postgresql://ekklesia:s3cr3t@postgres:5432/ekklesia",
"Authorization: Bearer eyJhbGciOi.payload.sig",
"EKKLESIA_IDENTITY_SECRET=0123456789abcdef",
].join("\n"),
);
for (const secret of [
"hunter2hunter2",
"abc/def+ghi",
"AKIAEXAMPLE",
"xyz123",
"s3cr3t",
"eyJhbGciOi",
"0123456789abcdef",
]) {
expect(output).not.toContain(secret);
}
expect(output).toContain("POSTGRES_PASSWORD=[redacted]");
expect(output).toContain("other=fine");
expect(output).toContain("postgresql://[redacted]@postgres:5432/ekklesia");
});
it("masks every occurrence of a supplied literal, wherever it appears", async () => {
const output = await redact("started with temporary-pw-12345 and again temporary-pw-12345", [
"temporary-pw-12345",
]);
expect(output).toBe("started with [redacted] and again [redacted]\n");
});
it("keeps the diagnosis itself readable", async () => {
const diagnosis =
"Error response from daemon: Bind for 127.0.0.1:8333 failed: port is already allocated";
expect(await redact(diagnosis)).toBe(`${diagnosis}\n`);
expect(await redact("duplicate key value violates unique constraint")).toBe(
"duplicate key value violates unique constraint\n",
);
expect(await redact('password authentication failed for user "ekklesia"')).toBe(
'password authentication failed for user "ekklesia"\n',
);
});
it("strips terminal control sequences from container logs", async () => {
expect(await redact("\u001b[2Kpostgres-1 | ready")).toBe("postgres-1 | ready\n");
});
});