gstack/bin/gstack-evidence

#!/usr/bin/env bun
/**
 * gstack-evidence — verification-evidence ledger: the mechanical arm of /ship's
 * IRON LAW ("no completion claims without fresh verification evidence").
 *
 *   gstack-evidence run --label <L> -- <cmd...>
 *   gstack-evidence check [--label <L> [--expect-cmd <exact string>]]... | --all
 *                         [--max-age <hours>] [--allow-paths <csv>]
 *
 * `run` is a TRANSPARENT wrapper: it streams the child's output through
 * unchanged, tees it to a 0600 log (2MB cap with a truncation marker), and
 * appends {ts, label, command, cmd_sha256, exit, duration_s, commit, tree,
 * dirty, wtree, log_path} to ~/.gstack/projects/<slug>/<branch>-evidence.jsonl.
 *
 * TRANSPARENCY INVARIANT (load-bearing): the child's exit code is ALWAYS the
 * wrapper's exit code. Every bookkeeping failure — ledger append, log dir,
 * non-git context, redact scan — is a stderr warning, never a failure. The
 * wrapper must never turn green tests red.
 *
 * Freshness binds to `wtree`, the working-tree content fingerprint from
 * bin/gstack-wtree: evidence recorded on uncommitted code stays FRESH after
 * the exact tested content is committed, and an untracked new source file
 * invalidates it. `cmd_sha256` = sha256 of the exact command string, no
 * normalization — the same convention as bin/gstack-verify-gate (which hashes
 * for TRUST; this ledger hashes for FRESHNESS).
 *
 * MACHINE-LOCAL by design: neither the ledger nor the logs are brain-synced.
 * A synced record citing an unsynced log would grade FRESH on a machine where
 * the log doesn't exist.
 *
 * `check` is read-only and never throws into the calling skill flow: any git
 * failure (gc'd stored tree, not a repo) degrades to STALE/MISSING. Call sites
 * must name expected labels explicitly — `--all` checks only labels that exist
 * in the ledger; it cannot prove that an expected lane ever ran.
 */

import { mkdirSync, openSync, writeSync, closeSync, readdirSync, statSync, unlinkSync, chmodSync, readFileSync } from "fs";
import { join, dirname } from "path";
import { spawnSync } from "child_process";
import { appendJsonl, readJsonl } from "../lib/jsonl-store";
import { scan, applyRedactions } from "../lib/redact-engine";

const BIN_DIR = dirname(Bun.fileURLToPath(import.meta.url));
const LOG_MAX_BYTES = 2 * 1024 * 1024;
const LOG_PRUNE_DAYS = 30;

interface EvidenceRecord {
  ts: string;
  label: string;
  command: string;
  cmd_sha256: string;
  exit: number;
  duration_s: number;
  commit?: string;
  tree?: string;
  dirty?: boolean;
  wtree?: string;
  log_path?: string;
  redacted?: boolean;
}

function warn(msg: string): void {
  console.error(`gstack-evidence: warning: ${msg}`);
}

function sha256(text: string): string {
  const h = new Bun.CryptoHasher("sha256");
  h.update(text);
  return h.digest("hex");
}

function git(args: string[]): string | undefined {
  try {
    const r = spawnSync("git", args, { encoding: "utf-8", timeout: 15000 });
    if (r.status !== 0) return undefined;
    const out = (r.stdout || "").trim();
    return out || undefined;
  } catch {
    return undefined;
  }
}

function currentWtree(): string | undefined {
  try {
    const r = spawnSync(join(BIN_DIR, "gstack-wtree"), { encoding: "utf-8", timeout: 30000 });
    if (r.status !== 0) return undefined;
    const out = (r.stdout || "").trim();
    return /^[0-9a-f]{40}$/.test(out) ? out : undefined;
  } catch {
    return undefined;
  }
}

function ledgerPath(): { dir: string; file: string; logsDir: string } {
  const home = process.env.GSTACK_HOME || (process.env.HOME ? join(process.env.HOME, ".gstack") : undefined);
  // No resolvable home: skip bookkeeping (a literal "~" dir in cwd would land
  // inside the repo and perturb the fingerprint it exists to compute).
  if (!home) throw new Error("no GSTACK_HOME/HOME — bookkeeping skipped");
  // ONE gstack-slug spawn: its output carries both SLUG= and BRANCH= lines
  // (same branch→filename sanitization as reviews.jsonl).
  const slugOut = spawnSync(join(BIN_DIR, "gstack-slug"), { encoding: "utf-8" });
  const sm = (slugOut.stdout || "").match(/^SLUG=(.+)$/m);
  const bm = (slugOut.stdout || "").match(/^BRANCH=(.+)$/m);
  const slug = sm ? sm[1].trim() : "unknown";
  const branch = bm ? bm[1].trim() : "no-branch";
  const dir = join(home, "projects", slug);
  return { dir, file: join(dir, `${branch}-evidence.jsonl`), logsDir: join(dir, "logs") };
}

/** Redact-engine pass over the command string. HIGH finding → store redacted. */
function safeCommandForRecord(command: string): { command: string; redacted: boolean } {
  try {
    const { findings } = scan(command);
    const high = findings.filter((f) => f.tier === "HIGH");
    if (high.length === 0) return { command, redacted: false };
    const redactedBody = applyRedactions(command, findings.map((f) => f.id)).body;
    const still = scan(redactedBody).findings.some((f) => f.tier === "HIGH");
    return { command: still ? "<redacted: HIGH credential in command>" : redactedBody, redacted: true };
  } catch {
    return { command, redacted: false };
  }
}

/** Opportunistic prune of logs older than LOG_PRUNE_DAYS. Best-effort. */
function pruneOldLogs(logsDir: string): void {
  try {
    const cutoff = Date.now() - LOG_PRUNE_DAYS * 24 * 3600 * 1000;
    for (const name of readdirSync(logsDir)) {
      const p = join(logsDir, name);
      try {
        if (statSync(p).mtimeMs < cutoff) unlinkSync(p);
      } catch {}
    }
  } catch {}
}

/** Exclusive-open a collision-safe log file. Returns undefined on failure. */
function openLog(logsDir: string, label: string, cmdSha: string): { fd: number; path: string } | undefined {
  try {
    mkdirSync(logsDir, { recursive: true });
    pruneOldLogs(logsDir);
    const ts = new Date().toISOString().replace(/[:.]/g, "-");
    const base = `${ts}-${label}-${process.pid}-${cmdSha.slice(0, 8)}`;
    for (let i = 0; i < 3; i++) {
      const p = join(logsDir, i === 0 ? `${base}.log` : `${base}-${i}.log`);
      try {
        const fd = openSync(p, "ax", 0o600);
        return { fd, path: p };
      } catch {}
    }
  } catch (e: any) {
    warn(`log setup failed (${e?.message ?? e}) — running unlogged`);
  }
  return undefined;
}

/**
 * Bun AUTO-LOADS `.env`, `.env.<NODE_ENV>` and `.env.local` from the working
 * directory into `process.env`. This file has a `#!/usr/bin/env bun` shebang, so
 * every command it spawns inherits those variables — and a repo `.env.local`
 * routinely holds PRODUCTION credentials.
 *
 * Two things go wrong, and the second one is worse than the leak:
 *
 *  1. Secrets reach a child process that would not have had them. `npm test` run
 *     by hand in the same shell sees none of this; run through the wrapper it sees
 *     all of it.
 *  2. THE COMMAND UNDER TEST BEHAVES DIFFERENTLY, so the evidence ledger
 *     certifies a run that is not the run CI performs. Observed in a Next.js repo
 *     2026-08-20: four tests failed 4/4 through the wrapper and passed 5/5 without
 *     it, because app code branched on env vars only the wrapper supplied. The
 *     wrapper exists to record trustworthy evidence, so silently changing the
 *     environment defeats its whole purpose.
 *
 * Verified against bun 1.3.11: a dotenv file does NOT override a variable the
 * shell already exported (the shell's value wins). So a key whose live value is
 * exactly the dotenv file's value was injected by bun, and dropping it restores
 * the environment the user's own shell would have given the command.
 *
 * Escape hatch: GSTACK_EVIDENCE_KEEP_DOTENV=1 keeps the old behaviour for anyone
 * who really does want the wrapper to supply .env values.
 */
const BUN_DOTENV_FILES = (): string[] => {
  const nodeEnv = process.env.NODE_ENV;
  // bun's documented precedence, lowest first. `.env.local` is skipped by bun
  // when NODE_ENV is "test"; mirror that rather than guessing.
  const files = [".env"];
  if (nodeEnv) files.push(`.env.${nodeEnv}`);
  if (nodeEnv !== "test") files.push(".env.local");
  return files;
};

/** Minimal dotenv reader: KEY=VALUE, one per line. Quotes stripped, comments and
 *  `export ` prefixes tolerated. Multi-line values are not parsed — a key we fail
 *  to parse is simply left in the child env, which is the safe direction.
 *  Known limitation: bun EXPANDS ${VAR} references inside dotenv values, but this
 *  reader compares the raw file text, so an expanded live value never matches and
 *  that key is left in the child env — the pre-scrub behavior persists for those
 *  keys (fails open, same safe direction as above). */
function parseDotenv(text: string): Map<string, string> {
  const out = new Map<string, string>();
  for (const raw of text.split(/\r?\n/)) {
    const line = raw.trim();
    if (!line || line.startsWith("#")) continue;
    const eq = line.indexOf("=");
    if (eq <= 0) continue;
    let key = line.slice(0, eq).trim();
    if (key.startsWith("export ")) key = key.slice(7).trim();
    if (!/^[A-Za-z_][A-Za-z0-9_]*$/.test(key)) continue;
    let val = line.slice(eq + 1).trim();
    if ((val.startsWith('"') && val.endsWith('"') && val.length > 1) ||
        (val.startsWith("'") && val.endsWith("'") && val.length > 1)) {
      val = val.slice(1, -1);
    }
    out.set(key, val);
  }
  return out;
}

/** process.env minus the variables bun injected from the repo's dotenv files.
 *  Returns the scrubbed env and the KEY NAMES removed (never the values). */
function childEnv(cwd: string): { env: Record<string, string>, scrubbed: string[] } {
  const env: Record<string, string> = {};
  for (const [k, v] of Object.entries(process.env)) if (v !== undefined) env[k] = v;
  if (process.env.GSTACK_EVIDENCE_KEEP_DOTENV === "1") return { env, scrubbed: [] };

  const scrubbed: string[] = [];
  for (const file of BUN_DOTENV_FILES()) {
    let text: string;
    try {
      text = readFileSync(join(cwd, file), "utf-8");
    } catch {
      continue; // absent or unreadable — nothing to scrub from it
    }
    for (const [k, v] of parseDotenv(text)) {
      // Only when the live value IS the file's value. A different live value means
      // the shell exported its own and bun left it alone, so it is genuinely the
      // user's environment and must survive.
      if (env[k] !== undefined && env[k] === v) {
        delete env[k];
        if (!scrubbed.includes(k)) scrubbed.push(k);
      }
    }
  }
  return { env, scrubbed };
}

async function cmdRun(argv: string[]): Promise<number> {
  let label = "default";
  const li = argv.indexOf("--label");
  const sep = argv.indexOf("--");
  if (li >= 0 && li + 1 < argv.length && (sep < 0 || li < sep)) label = argv[li + 1];
  if (sep < 0 || sep + 1 >= argv.length) {
    console.error("usage: gstack-evidence run --label <L> -- <cmd...>");
    return 2;
  }
  const cmdArgv = argv.slice(sep + 1);
  // Compound/piped commands pass as ONE string via bash -c; a multi-token argv
  // runs directly. The hashed command string is exact, no normalization.
  const commandString = cmdArgv.length === 1 ? cmdArgv[0] : cmdArgv.join(" ");
  const spawnArgv = cmdArgv.length === 1 ? ["bash", "-c", cmdArgv[0]] : cmdArgv;
  const cmdSha = sha256(commandString);
  label = label.replace(/[^a-zA-Z0-9._-]/g, "_");

  // Bookkeeping context — every piece is optional; failures only warn.
  let paths: ReturnType<typeof ledgerPath> | undefined;
  try {
    paths = ledgerPath();
    mkdirSync(paths.dir, { recursive: true });
  } catch (e: any) {
    warn(`ledger setup failed (${e?.message ?? e}) — result will not be recorded`);
  }
  const log = paths ? openLog(paths.logsDir, label, cmdSha) : undefined;

  // Fingerprint the content BEFORE the child runs: a working-tree edit made
  // DURING a long suite must not be certified as "the tested content".
  const wtreeBefore = currentWtree();

  const started = Date.now();
  let exitCode: number;
  let proc: ReturnType<typeof Bun.spawn> | undefined;
  try {
    const { env: spawnEnv, scrubbed } = childEnv(process.cwd());
    if (scrubbed.length > 0) {
      // Names only. Printing values here would defeat the point.
      warn(`scrubbed ${scrubbed.length} bun-injected dotenv var(s) from the child env: ${scrubbed.join(", ")} `
        + `(GSTACK_EVIDENCE_KEEP_DOTENV=1 to keep them)`);
    }
    proc = Bun.spawn(spawnArgv, { stdin: "inherit", stdout: "pipe", stderr: "pipe", env: spawnEnv });
  } catch (e: any) {
    // Spawn failure (ENOENT on argv-direct form): record exit 127, propagate 127.
    exitCode = 127;
    warn(`spawn failed: ${e?.message ?? e}`);
    record(paths, log?.path, label, commandString, cmdSha, exitCode, started, wtreeBefore);
    return exitCode;
  }

  // Stream-tee: forward chunks as they arrive (never buffer — E2E logs are MBs).
  let logBytes = 0;
  let truncated = false;
  const teeToLog = (chunk: Uint8Array) => {
    if (!log || truncated) return;
    try {
      if (logBytes + chunk.byteLength > LOG_MAX_BYTES) {
        const room = LOG_MAX_BYTES - logBytes;
        if (room > 0) writeSync(log.fd, chunk.subarray(0, room));
        writeSync(log.fd, Buffer.from("\n\n[gstack-evidence: log truncated at 2MB — output continued on console]\n"));
        truncated = true;
      } else {
        writeSync(log.fd, chunk);
        logBytes += chunk.byteLength;
      }
    } catch {
      truncated = true; // stop teeing on any write failure; console stream continues
      try {
        writeSync(log.fd, Buffer.from("\n\n[gstack-evidence: log ended early (write failure) — output continued on console]\n"));
      } catch {}
    }
  };
  const pump = async (stream: ReadableStream<Uint8Array> | undefined, out: NodeJS.WriteStream) => {
    if (!stream) return;
    for await (const chunk of stream) {
      // Honor backpressure: when the console consumer is slower than the child
      // (piped into a pager/log collector), wait for drain instead of queueing
      // unbounded chunks in the WriteStream buffer.
      if (!out.write(chunk)) {
        // Race drain against error: a dying consumer (EPIPE from `| head`)
        // never drains — resolve either way and stop forwarding on error.
        await new Promise<void>((r) => {
          const done = () => {
            out.off("drain", done);
            out.off("error", done);
            r();
          };
          out.once("drain", done);
          out.once("error", done);
        });
      }
      teeToLog(chunk);
    }
  };
  try {
    await Promise.all([pump(proc.stdout as any, process.stdout), pump(proc.stderr as any, process.stderr)]);
    exitCode = await proc.exited;
    if (exitCode === null || exitCode === undefined) exitCode = 1;
  } catch (e: any) {
    warn(`stream error: ${e?.message ?? e}`);
    try {
      exitCode = await proc.exited;
    } catch {
      exitCode = 1;
    }
  } finally {
    if (log) {
      try {
        closeSync(log.fd);
      } catch {}
    }
  }

  record(paths, log?.path, label, commandString, cmdSha, exitCode, started, wtreeBefore);
  return exitCode;
}

function record(
  paths: { dir: string; file: string } | undefined,
  logPath: string | undefined,
  label: string,
  commandString: string,
  cmdSha: string,
  exitCode: number,
  startedMs: number,
  wtreeBefore: string | undefined,
): void {
  if (!paths) return;
  try {
    const { command, redacted } = safeCommandForRecord(commandString);
    const rec: EvidenceRecord = {
      ts: new Date().toISOString(),
      label,
      command,
      cmd_sha256: cmdSha,
      exit: exitCode,
      duration_s: Math.round((Date.now() - startedMs) / 100) / 10,
    };
    if (redacted) rec.redacted = true;
    const commit = git(["rev-parse", "HEAD"]);
    if (commit) {
      rec.commit = commit;
      rec.tree = git(["rev-parse", "HEAD^{tree}"]);
      rec.dirty = (git(["status", "--porcelain", "-uno"]) ?? "") !== "";
      // TOCTOU guard: the fingerprint is only trustworthy when the content was
      // IDENTICAL before and after the run. A mid-run edit omits wtree, so
      // check grades STALE instead of certifying content the suite never ran.
      const wtreeAfter = currentWtree();
      if (wtreeBefore && wtreeAfter && wtreeBefore === wtreeAfter) {
        rec.wtree = wtreeAfter;
      } else if (wtreeBefore || wtreeAfter) {
        warn("working-tree content changed during the run — evidence recorded without a content fingerprint (will grade STALE)");
      }
    }
    if (logPath) rec.log_path = logPath;
    appendJsonl(paths.file, rec, { mode: 0o600 });
    try {
      chmodSync(paths.file, 0o600);
    } catch {}
    // Summary line on stderr so calling agents get the exit + log path even
    // when the lane ran backgrounded. Never on stdout (stays transparent).
    console.error(`gstack-evidence: recorded label=${label} exit=${exitCode} log=${logPath ?? "-"}`);
  } catch (e: any) {
    warn(`ledger append failed (${e?.message ?? e}) — the command result stands`);
  }
}

function cmdCheck(argv: string[]): number {
  // Parse: repeated --label, each optionally followed (anywhere later) by its
  // own --expect-cmd; pairing is positional — an --expect-cmd binds to the most
  // recent --label before it.
  const wanted: { label: string; expectCmd?: string }[] = [];
  let all = false;
  let maxAgeHours: number | undefined;
  let allowPaths: string[] = [];
  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];
    if (a === "--label") wanted.push({ label: argv[++i] ?? "" });
    else if (a === "--expect-cmd") {
      if (wanted.length === 0) {
        console.error("gstack-evidence: --expect-cmd requires a preceding --label");
        return 2;
      }
      wanted[wanted.length - 1].expectCmd = argv[++i] ?? "";
    } else if (a === "--all") all = true;
    else if (a === "--max-age") {
      maxAgeHours = Number(argv[++i]);
      if (!Number.isFinite(maxAgeHours) || maxAgeHours <= 0) {
        // A typo must never silently drop the age gate (fail open) on a
        // freshness checker: it is a usage error.
        console.error(`gstack-evidence: --max-age must be a positive number of hours, got: ${JSON.stringify(argv[i])}`);
        return 2;
      }
    }
    else if (a === "--allow-paths") allowPaths = (argv[++i] ?? "").split(",").map((s) => s.trim()).filter(Boolean);
  }
  if (!all && wanted.length === 0) {
    console.error("usage: gstack-evidence check [--label <L> [--expect-cmd <s>]]... | --all  [--max-age <hrs>] [--allow-paths <csv>]");
    return 2;
  }

  let records: EvidenceRecord[] = [];
  try {
    records = readJsonl<EvidenceRecord>(ledgerPath().file);
  } catch {
    records = [];
  }

  const labels = all
    ? [...new Set(records.map((r) => r.label))].map((label) => ({ label, expectCmd: undefined as string | undefined }))
    : wanted;
  if (all && labels.length === 0) {
    console.log("EVIDENCE: MISSING (ledger empty — no labels recorded)");
    return 1;
  }

  const wtreeNow = currentWtree();
  let allFresh = true;
  for (const { label, expectCmd } of labels) {
    const latest = records.findLast((r) => r.label === label);
    if (!latest) {
      console.log(`EVIDENCE: MISSING label=${label}`);
      allFresh = false;
      continue;
    }
    const detail = `label=${label} exit=${latest.exit} ts=${latest.ts}${latest.log_path ? ` log=${latest.log_path}` : ""}`;
    let verdict: "FRESH" | "STALE" = "FRESH";
    let reason = "";
    if (latest.exit !== 0) {
      verdict = "STALE";
      reason = "recorded run failed";
    } else if (maxAgeHours !== undefined) {
      const ageMs = Date.now() - Date.parse(latest.ts);
      if (!(ageMs >= 0 && ageMs <= maxAgeHours * 3600 * 1000)) {
        verdict = "STALE";
        reason = `older than ${maxAgeHours}h`;
      }
    }
    if (verdict === "FRESH" && expectCmd !== undefined && sha256(expectCmd) !== latest.cmd_sha256) {
      verdict = "STALE";
      reason = "command changed (cmd_sha256 mismatch)";
    }
    if (verdict === "FRESH") {
      // Content binding: identical working-tree fingerprint, or a diff confined
      // to the allow-list. Any git failure (gc'd tree, not a repo) → STALE —
      // never an error into the calling flow.
      if (!latest.wtree || !/^[0-9a-f]{40}$/.test(latest.wtree) || !wtreeNow) {
        // Stored fingerprints are re-validated before reaching git argv — a
        // forged/corrupt ledger line must degrade, never inject options.
        verdict = "STALE";
        reason = !latest.wtree
          ? "record has no content fingerprint"
          : !/^[0-9a-f]{40}$/.test(latest.wtree)
            ? "record has malformed fingerprint"
            : "current fingerprint unavailable";
      } else if (latest.wtree !== wtreeNow) {
        const diff = git(["diff", "--name-only", latest.wtree, wtreeNow]);
        if (diff === undefined) {
          verdict = "STALE";
          reason = "content changed (fingerprint diff unavailable)";
        } else {
          const changed = diff.split("\n").map((s) => s.trim()).filter(Boolean);
          const outside = changed.filter((f) => !allowPaths.some((a) => f === a || f.startsWith(a.replace(/\/$/, "") + "/")));
          if (changed.length === 0 || outside.length === 0) {
            reason = changed.length ? `diff confined to allow-paths (${changed.length} file(s))` : "";
          } else {
            verdict = "STALE";
            reason = `content changed: ${outside.slice(0, 5).join(", ")}${outside.length > 5 ? ", ..." : ""}`;
          }
        }
      }
    }
    console.log(`EVIDENCE: ${verdict} ${detail}${reason ? ` reason=${reason}` : ""}`);
    if (verdict !== "FRESH") allFresh = false;
  }
  return allFresh ? 0 : 1;
}

const [, , sub, ...rest] = process.argv;
try {
  if (sub === "run") {
    process.exit(await cmdRun(rest));
  } else if (sub === "check") {
    process.exit(cmdCheck(rest));
  } else {
    console.error("usage: gstack-evidence run|check ...");
    process.exit(2);
  }
} catch (e: any) {
  // Never let the wrapper's own failure look like a command failure in a way
  // that breaks a skill flow: `run` propagates the child's code from inside
  // cmdRun; reaching here means bookkeeping blew up outside it.
  warn(`unexpected error: ${e?.message ?? e}`);
  process.exit(1);
}