Files
everything-claude-code/scripts/codex/merge-mcp-config.js
Affaan Mustafa 6319c7d309 fix: stability batch — hook stdin truncation, Codex exa TOML, Stop hook JSON, GateGuard repetition (#2227)
* fix(hooks): fail open on oversized stdin instead of echoing truncated JSON (#2222)

run-with-flags.js capped stdin at 1MB but every fallthrough path still
echoed the truncated string to stdout. The harness parses hook stdout as
JSON, got a document cut mid-stream, and blocked the tool call — so any
Edit/Write with a >1MB hook payload was permanently blocked by every
registered pre-write hook, before ECC_HOOK_PROFILE / ECC_DISABLED_HOOKS
gating could run.

- Exit 0 with empty stdout (no opinion) when the stdin cap trips, before
  any echo or gating logic.
- Flush stdout via write callback before process.exit: exiting right
  after stdout.write() dropped everything past the ~64KB pipe buffer,
  cutting even sub-cap pass-through payloads mid-JSON.

Regression tests cover the enabled, disabled, and missing-arg paths for
oversized payloads plus full echo of sub-cap >64KB payloads.

* fix(codex): stop emitting invalid exa url entry, align merge with connector policy (#2224)

The Codex MCP merge declared exa with a url key, but Codex's
[mcp_servers.*] TOML schema is stdio-only — the url key makes the
entire config.toml fail to load, bricking both the codex CLI and the
desktop app. Every install/update re-injected the line because the
urlEntry branch treated the broken entry as present.

- ECC_SERVERS now emits only the current default set per
  docs/MCP-CONNECTOR-POLICY.md: chrome-devtools (stdio, command/args).
  Retired servers (supabase, playwright, context7, exa, github, memory,
  sequential-thinking) are never re-emitted; existing user-managed
  entries are untouched.
- The merge now repairs the exact ECC-emitted broken form (url-only
  exa entry) on every run so re-running the installer fixes broken
  configs instead of preserving them. User stdio exa entries
  (command + mcp-remote) are left alone.
- check-codex-global-state.sh requires chrome-devtools instead of the
  retired set, and flags url-only exa entries with a repair hint.

Tests cover repair, re-run idempotence, stdio-entry preservation, and
no-retired-server emission in add, update, dry-run, and disabled modes.

* fix(hooks): never echo truncated stdin from Stop hooks (#2090)

Stop hooks follow the ECC pass-through convention (echo stdin on
stdout), but every echoing Stop hook capped stdin and echoed the capped
string. The Stop payload carries last_assistant_message, so a long
final assistant message produced a JSON document cut mid-stream on
stdout, which the harness reports as 'Stop hook error: JSON validation
failed' across the whole Stop chain.

Reproduced: a Stop payload with a >64KB last_assistant_message run
through run-with-flags + cost-tracker emitted exactly 65536 bytes of
invalid JSON (cost-tracker capped stdin at 64KB — far below realistic
Stop payloads).

- cost-tracker: raise the cap to 1MB (matching all other hooks) and
  suppress the pass-through echo when stdin was truncated.
- check-console-log, stop-format-typecheck, desktop-notify: suppress
  the echo when stdin was truncated; flush stdout before process.exit
  so sub-cap payloads are not cut at the ~64KB pipe buffer.
- All hooks keep exiting 0 (fail-open); diagnostics go to stderr.

New stop-hooks-stdout test asserts the contract for every registered
Stop hook: stdout is empty or valid JSON, exit code 0 — for realistic
100KB payloads and oversized >1MB payloads, via the production runner
and via direct invocation. Updated the old hooks.test.js case that
codified the truncated-echo behavior.

* fix(hooks): dampen GateGuard fact-force repetition in long sessions (#2142)

In long autonomous sessions the fact-force gate produced 10+
near-identical 'state facts -> blocked -> restate -> retry' blocks in
one context window, which measurably raises the odds of the model
collapsing into a degenerate single-token repetition loop.

- Track a per-session fact_force_denials counter in GateGuard state
  (merged max across concurrent writers, reset with the session, robust
  to malformed on-disk values).
- The first GATEGUARD_FACT_FORCE_FULL_DENIALS denials (default 3) keep
  the full four-fact block; later denials emit a condensed single-line
  message that carries the denial ordinal, so consecutive denials are
  structurally different and never textually identical.
- True retries of the same target remain allowed without re-prompting
  (unchanged). Destructive-Bash and routine-Bash gates are unchanged,
  as are the ECC_GATEGUARD=off / ECC_DISABLED_HOOKS escape hatches.

Eight new tests cover budget counting, condensed format, ordinal
advancement, retry pass-through, env tuning, malformed state, MultiEdit
dampening, and destructive-gate exemption.

* fix(hooks): keep security hooks able to block on oversized stdin (#2222)

Refine the truncation fail-open: instead of skipping the hook entirely,
the runner now suppresses only its own raw-echo when stdin was
truncated. The hook still executes and receives the truncated flag
(run() context / ECC_HOOK_INPUT_TRUNCATED), so config-protection keeps
blocking truncated protected-config payloads (its test requires exit 2)
while pass-through hooks fail open with empty stdout as before.

* style: apply repo formatter to touched hook files
2026-06-11 00:31:33 -04:00

353 lines
13 KiB
JavaScript

#!/usr/bin/env node
'use strict';
/**
* Merge ECC-recommended MCP servers into a Codex config.toml.
*
* Strategy: ADD-ONLY by default.
* - Parse the TOML to detect which mcp_servers.* sections exist.
* - Append raw TOML text for any missing servers (preserves existing file byte-for-byte).
* - Log warnings when an existing server's config differs from the ECC recommendation.
* - With --update-mcp, also replace existing ECC-managed servers.
*
* Uses the repo's package-manager abstraction (scripts/lib/package-manager.js)
* so MCP launcher commands respect the user's configured package manager.
*
* Usage:
* node merge-mcp-config.js <config.toml> [--dry-run] [--update-mcp]
*/
const fs = require('fs');
const path = require('path');
const { parseDisabledMcpServers } = require('../lib/mcp-config');
let TOML;
try {
TOML = require('@iarna/toml');
} catch {
console.error('[ecc-mcp] Missing dependency: @iarna/toml');
console.error('[ecc-mcp] Run: npm install (from the ECC repo root)');
process.exit(1);
}
// ---------------------------------------------------------------------------
// Package manager detection
// ---------------------------------------------------------------------------
let pmConfig;
try {
const { getPackageManager } = require(path.join(__dirname, '..', 'lib', 'package-manager.js'));
pmConfig = getPackageManager();
} catch {
// Fallback: if package-manager.js isn't available, default to npx
pmConfig = { name: 'npm', config: { name: 'npm', execCmd: 'npx' } };
}
// Yarn 1.x doesn't support `yarn dlx` — fall back to npx for classic Yarn.
let resolvedExecCmd = pmConfig.config.execCmd;
if (pmConfig.name === 'yarn' && resolvedExecCmd === 'yarn dlx') {
try {
const { execFileSync } = require('child_process');
const ver = execFileSync('yarn', ['--version'], { encoding: 'utf8', timeout: 5000 }).trim();
if (ver.startsWith('1.')) {
resolvedExecCmd = 'npx';
}
} catch {
// Can't detect version — keep yarn dlx and let it fail visibly
}
}
const PM_NAME = pmConfig.config.name || pmConfig.name;
const PM_EXEC = resolvedExecCmd; // e.g. "pnpm dlx", "npx", "bunx", "yarn dlx"
const PM_EXEC_PARTS = PM_EXEC.split(/\s+/); // ["pnpm", "dlx"] or ["npx"] or ["bunx"]
// ---------------------------------------------------------------------------
// ECC-recommended MCP servers
// ---------------------------------------------------------------------------
/**
* Build a server spec with the detected package manager.
* Returns { fields, toml } where fields is for drift detection and
* toml is the raw text appended to the file.
*
* Codex's [mcp_servers.*] TOML schema is stdio-only (command/args) —
* never emit a `url` key here. The http/url form is valid only for
* Claude Code's .mcp.json (#2224).
*/
function dlxServer(name, pkg, extraFields, extraToml) {
const args = [...PM_EXEC_PARTS.slice(1), pkg];
const fields = { command: PM_EXEC_PARTS[0], args, ...extraFields };
const argsStr = JSON.stringify(args).replace(/,/g, ', ');
let toml = `[mcp_servers.${name}]\ncommand = "${PM_EXEC_PARTS[0]}"\nargs = ${argsStr}`;
if (extraToml) toml += '\n' + extraToml;
return { fields, toml };
}
/** Each entry: key = section name under mcp_servers, value = { toml, fields } */
const DEFAULT_MCP_STARTUP_TIMEOUT_SEC = 30;
const DEFAULT_MCP_STARTUP_TIMEOUT_TOML = `startup_timeout_sec = ${DEFAULT_MCP_STARTUP_TIMEOUT_SEC}`;
// Current default connector set (docs/MCP-CONNECTOR-POLICY.md): exactly one
// connector. The former defaults (supabase, playwright, context7, exa,
// github, memory, sequential-thinking) were retired in the June 2026 audit
// and must not be re-emitted; they remain opt-in via
// mcp-configs/mcp-servers.json. Existing user-managed entries are never
// touched by the merge (add-only), except the known-invalid repair below.
const ECC_SERVERS = {
'chrome-devtools': dlxServer('chrome-devtools', 'chrome-devtools-mcp@latest', { startup_timeout_sec: DEFAULT_MCP_STARTUP_TIMEOUT_SEC }, DEFAULT_MCP_STARTUP_TIMEOUT_TOML)
};
// ECC <= 2.0.0 emitted [mcp_servers.exa] with a `url` key. Codex rejects
// `url` for stdio servers, which makes the *entire* config.toml fail to
// load (#2224). Repair exactly that ECC-emitted form on every merge so
// re-running the installer fixes broken configs instead of preserving
// them. A user-managed stdio exa entry (command/args) is left untouched.
const RETIRED_INVALID_URL_SERVERS = {
exa: 'https://mcp.exa.ai/mcp'
};
// Legacy section names that should be treated as an existing ECC server.
// e.g. older configs shipped [mcp_servers.context7-mcp] instead of
// [mcp_servers.context7]. Empty since the June 2026 default-set reduction.
const LEGACY_ALIASES = {};
// ---------------------------------------------------------------------------
// Helpers
// ---------------------------------------------------------------------------
function log(msg) {
console.log(`[ecc-mcp] ${msg}`);
}
function warn(msg) {
console.warn(`[ecc-mcp] WARNING: ${msg}`);
}
/** Shallow-compare two objects (one level deep, arrays by JSON). */
function configDiffers(existing, recommended) {
for (const key of Object.keys(recommended)) {
const a = existing[key];
const b = recommended[key];
if (Array.isArray(b)) {
if (JSON.stringify(a) !== JSON.stringify(b)) return true;
} else if (a !== b) {
return true;
}
}
return false;
}
/**
* Remove a TOML section and its key-value pairs from raw text.
* Matches the section header even if followed by inline comments or whitespace
* (e.g. `[mcp_servers.github] # comment`).
* Returns the text with the section removed.
*/
function removeSectionFromText(text, sectionHeader) {
const escaped = sectionHeader.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
const headerPattern = new RegExp(`^${escaped}(\\s*(#.*)?)?$`);
const lines = text.split('\n');
const result = [];
let skipping = false;
for (const line of lines) {
const trimmed = line.replace(/\r$/, '');
if (headerPattern.test(trimmed)) {
skipping = true;
continue;
}
if (skipping && /^\[/.test(trimmed)) {
skipping = false;
}
if (!skipping) {
result.push(line);
}
}
return result.join('\n');
}
/**
* Collect all TOML sub-section headers for a given server name.
* @iarna/toml nests subtables, so `[mcp_servers.supabase.env]` appears as
* `parsed.mcp_servers.supabase.env` (nested), NOT as a flat dotted key.
* Walk the nested object to find sub-objects that represent TOML sub-tables.
*/
function findSubSections(serverObj, prefix) {
const sections = [];
if (!serverObj || typeof serverObj !== 'object') return sections;
for (const key of Object.keys(serverObj)) {
const val = serverObj[key];
if (val && typeof val === 'object' && !Array.isArray(val)) {
const subPath = `${prefix}.${key}`;
sections.push(subPath);
sections.push(...findSubSections(val, subPath));
}
}
return sections;
}
/**
* Remove a server and all its sub-sections from raw TOML text.
* Uses findSubSections to walk the parsed nested object (not flat keys).
*/
function removeServerFromText(raw, serverName, existing) {
let result = removeSectionFromText(raw, `[mcp_servers.${serverName}]`);
const serverObj = existing[serverName];
if (serverObj) {
for (const sub of findSubSections(serverObj, serverName)) {
result = removeSectionFromText(result, `[mcp_servers.${sub}]`);
}
}
return result;
}
// ---------------------------------------------------------------------------
// Main
// ---------------------------------------------------------------------------
function main() {
const args = process.argv.slice(2);
const configPath = args.find(a => !a.startsWith('-'));
const dryRun = args.includes('--dry-run');
const updateMcp = args.includes('--update-mcp');
const disabledServers = new Set(parseDisabledMcpServers(process.env.ECC_DISABLED_MCPS));
if (!configPath) {
console.error('Usage: merge-mcp-config.js <config.toml> [--dry-run] [--update-mcp]');
process.exit(1);
}
if (!fs.existsSync(configPath)) {
console.error(`[ecc-mcp] Config file not found: ${configPath}`);
process.exit(1);
}
log(`Package manager: ${PM_NAME} (exec: ${PM_EXEC})`);
if (disabledServers.size > 0) {
log(`Disabled via ECC_DISABLED_MCPS: ${[...disabledServers].join(', ')}`);
}
let raw = fs.readFileSync(configPath, 'utf8');
let parsed;
try {
parsed = TOML.parse(raw);
} catch (err) {
console.error(`[ecc-mcp] Failed to parse ${configPath}: ${err.message}`);
process.exit(1);
}
const existing = parsed.mcp_servers || {};
const toAppend = [];
const toRemoveLog = [];
// Repair schema-invalid entries emitted by earlier ECC versions (#2224).
for (const [name, invalidUrl] of Object.entries(RETIRED_INVALID_URL_SERVERS)) {
const entry = existing[name];
const isBrokenEccForm =
entry &&
typeof entry.url === 'string' &&
entry.url === invalidUrl &&
typeof entry.command !== 'string';
if (isBrokenEccForm) {
toRemoveLog.push(`mcp_servers.${name} (invalid url entry from earlier ECC versions)`);
raw = removeServerFromText(raw, name, existing);
log(` [repair] mcp_servers.${name} — url is not valid for Codex stdio servers, removing`);
}
}
for (const [name, spec] of Object.entries(ECC_SERVERS)) {
const entry = existing[name];
const aliases = LEGACY_ALIASES[name] || [];
const legacyName = aliases.find(a => existing[a] && typeof existing[a].command === 'string');
// Prefer canonical entry over legacy alias
const hasCanonical = entry && typeof entry.command === 'string';
const resolvedEntry = hasCanonical ? entry : legacyName ? existing[legacyName] : null;
// Recognize url-form entries as existing so they are never duplicated.
// (Codex itself rejects url-form stdio servers; ECC only ever emits
// command/args, but a user-managed entry must still count as present.)
const urlEntry = !resolvedEntry && entry && typeof entry.url === 'string' ? entry : null;
const finalEntry = resolvedEntry || urlEntry;
const resolvedLabel = hasCanonical ? name : legacyName || name;
if (disabledServers.has(name)) {
if (finalEntry) {
toRemoveLog.push(`mcp_servers.${resolvedLabel} (disabled)`);
raw = removeServerFromText(raw, resolvedLabel, existing);
if (resolvedLabel !== name) {
raw = removeServerFromText(raw, name, existing);
}
}
log(` [skip] mcp_servers.${name} (disabled)`);
continue;
}
if (finalEntry) {
if (updateMcp) {
// --update-mcp: remove existing section (and legacy alias), will re-add below
toRemoveLog.push(`mcp_servers.${resolvedLabel}`);
raw = removeServerFromText(raw, resolvedLabel, existing);
if (resolvedLabel !== name) {
raw = removeServerFromText(raw, name, existing);
}
if (legacyName && hasCanonical) {
toRemoveLog.push(`mcp_servers.${legacyName}`);
raw = removeServerFromText(raw, legacyName, existing);
}
toAppend.push(spec.toml);
} else {
// Add-only mode: skip, but warn about drift
if (legacyName && !hasCanonical) {
warn(`mcp_servers.${legacyName} is a legacy name for ${name} (run with --update-mcp to migrate)`);
} else if (configDiffers(finalEntry, spec.fields)) {
warn(`mcp_servers.${name} differs from ECC recommendation (run with --update-mcp to refresh)`);
} else {
log(` [ok] mcp_servers.${name}`);
}
}
} else {
log(` [add] mcp_servers.${name}`);
toAppend.push(spec.toml);
}
}
const hasRemovals = toRemoveLog.length > 0;
if (toAppend.length === 0 && !hasRemovals) {
log('All ECC MCP servers already present. Nothing to do.');
return;
}
const appendText = '\n' + toAppend.join('\n\n') + '\n';
if (dryRun) {
if (toRemoveLog.length > 0) {
log('Dry run — would remove:');
for (const label of toRemoveLog) log(` [remove] ${label}`);
}
if (toAppend.length > 0) {
log('Dry run — would append:');
console.log(appendText);
}
return;
}
// Write: for add-only, append to preserve existing content byte-for-byte.
// For --update-mcp, we modified `raw` above, so write the full file + appended sections.
if (updateMcp || hasRemovals) {
for (const label of toRemoveLog) log(` [update] ${label}`);
const cleaned = raw.replace(/\n+$/, '\n');
fs.writeFileSync(configPath, cleaned + (toAppend.length > 0 ? appendText : ''), 'utf8');
} else {
fs.appendFileSync(configPath, appendText, 'utf8');
}
if (hasRemovals && toAppend.length === 0) {
log(`Done. Removed ${toRemoveLog.length} server section(s).`);
return;
}
log(`Done. ${toAppend.length} server(s) ${updateMcp ? 'updated' : 'added'}.`);
}
main();