Files
shockbot/utils/gitAuth.ts
T
David Blass b6e2c61d30 fix(push_branch): retry transient push errors and surface full stderr/stdout (#573)
* fix(push_branch): retry transient push errors and surface full stderr/stdout

issue #571 motivated three small improvements to `mcp__pullfrog__push_branch`:

1. classify push errors into `concurrent-push` / `transient` / `unknown`.
   - `concurrent-push` extends the existing `fetch first` / `non-fast-forward`
     matcher to also catch the server-side `cannot lock ref` form (the case
     #571 reports). all three route to the same fetch + integrate + retry
     recovery message; copy now mentions concurrent push as a likely cause.
   - `transient` covers RPC failed, early EOF, connection reset, dns flake,
     HTTP 5xx, HTTP/2 stream not closed, and unexpected sideband disconnect.
     these are retried in-tool with 2s + 5s backoff before surfacing the
     error. push is idempotent so verbatim retry is safe.
   - `unknown` (auth/permission/protected-branch/4xx) is rethrown unchanged —
     retrying these wastes time and noise.

2. surface stdout alongside stderr in `$git` failure messages and include the
   exit code. previously only `stderr.trim()` was forwarded, which could be
   empty in rare HTTPS failure modes (the agent on issue #571's run saw a
   one-line `failed to push some refs` and had nothing to diagnose with).

3. unit tests for the classifier covering all three branches plus the
   concurrent-push-wins-over-transient ordering.

does not introduce auto fetch+rebase+retry inside the tool — that path is
blocked under shell=disabled, can leave the working tree mid-conflict, and
would create unwanted merge commits. the recovery message keeps the agent
in the loop.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(push_branch): retry 429, jitter backoff, downgrade retry log to info

- treat HTTP 429 (rate-limit / abuse detection) as transient — GitHub
  occasionally surfaces it on git push, where it is retry-safe unlike
  401/403/404
- add ±25% jitter to backoff so concurrent agents hit by the same
  upstream blip don't retry in lockstep
- log retries with log.info instead of log.warning to match retry.ts
  convention; a successful retry shouldn't leave a yellow GHA annotation
  behind in the job summary

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
2026-05-05 21:59:40 +00:00

184 lines
5.5 KiB
TypeScript

/**
* git authentication via GIT_ASKPASS.
*
* a localhost HTTP server serves tokens via single-use UUID codes.
* each $git() call writes a unique askpass script with the server
* port+code baked into the file body — no secrets in subprocess env.
*
* see wiki/askpass.md for full security documentation.
*/
import { execSync } from "node:child_process";
import { createHash } from "node:crypto";
import { readFileSync, realpathSync, unlinkSync } from "node:fs";
import { log } from "./cli.ts";
import type { GitAuthServer } from "./gitAuthServer.ts";
import { filterEnv } from "./secrets.ts";
import { spawn } from "./subprocess.ts";
type SafeGitSubcommand = "fetch" | "push";
type GitAuthOptions = {
token: string;
cwd?: string;
};
type GitResult = {
stdout: string;
stderr: string;
};
// --- git binary resolution and tamper detection ---
type GitBinaryInfo = {
path: string;
sha256: string;
};
let gitBinary: GitBinaryInfo | undefined;
function hashFile(path: string): string {
return createHash("sha256").update(readFileSync(path)).digest("hex");
}
/**
* resolve and fingerprint the git binary. must be called once at startup
* (in main()) before any agent code runs, so the path and hash reflect
* the untampered binary.
*
* resolves symlinks via realpath so the hash is of the actual binary.
* a malicious agent with sudo could replace the binary later, which is
* caught by verifyGitBinary() before each authenticated call.
*/
export function resolveGit(): void {
const whichPath = execSync("which git", { encoding: "utf-8" }).trim();
const resolvedPath = realpathSync(whichPath);
const sha256 = hashFile(resolvedPath);
gitBinary = { path: resolvedPath, sha256 };
log.debug(`» git binary: ${resolvedPath} (sha256: ${sha256.slice(0, 12)}...)`);
}
function verifyGitBinary(): string {
if (!gitBinary) {
throw new Error("git binary not initialized — call resolveGit() at startup");
}
const currentHash = hashFile(gitBinary.path);
if (currentHash !== gitBinary.sha256) {
throw new Error(
`git binary tampered: expected sha256 ${gitBinary.sha256}, got ${currentHash}. ` +
`path: ${gitBinary.path}`
);
}
return gitBinary.path;
}
// --- auth server ---
let authServer: GitAuthServer | undefined;
export function setGitAuthServer(server: GitAuthServer): void {
authServer = server;
}
/**
* execute authenticated git command via ASKPASS.
*
* subcommand is restricted to "fetch" | "push" — operations that talk to
* a remote and need credentials. working-tree operations (checkout, merge)
* use $() from shell.ts which has no token.
*
* per call: registers a one-time code with the auth server, writes a
* unique askpass script with port+code baked in, spawns git with
* GIT_ASKPASS pointing to the script, and deletes the script in finally.
*
* @example
* await $git("fetch", ["origin", "main"], { token });
* await $git("push", ["-u", "origin", "feature"], { token });
*/
export async function $git(
subcommand: SafeGitSubcommand,
args: string[],
options: GitAuthOptions
): Promise<GitResult> {
const gitPath = verifyGitBinary();
if (!authServer) {
throw new Error("git auth server not initialized — call setGitAuthServer() at startup");
}
const cwd = options.cwd ?? process.cwd();
const code = authServer.register(options.token);
const scriptPath = authServer.writeAskpassScript(code);
// -c flags override local .git/config — defense-in-depth against
// agent-set config that could spawn subprocesses before ASKPASS runs
const fullArgs = [
"-c",
"core.fsmonitor=false",
"-c",
"credential.helper=",
"-c",
"protocol.file.allow=never",
"-c",
"core.sshCommand=ssh",
subcommand,
...args,
];
log.debug(`git ${fullArgs.join(" ")}`);
try {
const result = await spawn({
cmd: gitPath,
args: fullArgs,
cwd,
env: {
...filterEnv(),
GIT_ASKPASS: scriptPath,
GIT_TERMINAL_PROMPT: "0",
// blocks env-based git config injection from outer processes.
// GIT_CONFIG_COUNT=0 blocks the newer KEY_n/VALUE_n mechanism.
// GIT_CONFIG_PARAMETERS="" clears the legacy quoted-list mechanism.
// both are needed — they are independent systems.
GIT_CONFIG_COUNT: "0",
GIT_CONFIG_PARAMETERS: "",
},
activityTimeout: 0,
});
if (result.stderr.includes("askpass-compromised")) {
log.info("askpass code was already consumed — token has been revoked");
throw new Error("git auth failed — askpass code was already consumed, token revoked");
}
if (result.exitCode !== 0) {
const stderr = result.stderr.trim();
const stdout = result.stdout.trim();
// stderr is the primary channel for git diagnostics, but in rare cases
// (e.g. some HTTPS smart-protocol failures) the only useful detail is
// on stdout — without it the agent / operator sees an empty error.
// include exit code so we can distinguish e.g. signal-killed (1 with
// empty output) from a genuine git-level rejection.
const detail =
stderr && stdout
? `${stderr}\n--- stdout ---\n${stdout}`
: stderr || stdout || "(no output)";
const message = `git ${subcommand} failed (exit ${result.exitCode}): ${detail}`;
log.info(message);
throw new Error(message);
}
return {
stdout: result.stdout.trim(),
stderr: result.stderr.trim(),
};
} finally {
try {
unlinkSync(scriptPath);
} catch {
// script may have self-deleted already
}
}
}