mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 03:35:09 +02:00
04b709d91a
* test: add golden-file baselines for host config refactor Snapshot generated SKILL.md output for ship skill across all 3 existing hosts (Claude, Codex, Factory). These baselines verify the config-driven refactor produces identical output to the current hardcoded system. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add HostConfig interface and validator for declarative host system New scripts/host-config.ts defines the typed HostConfig interface that captures all per-host variation: paths, frontmatter rules, path/tool rewrites, suppressed resolvers, runtime root symlinks, install strategy, and behavioral config (co-author trailer, learnings mode, boundary instruction). Includes validateHostConfig() and validateAllConfigs() with regex-based security validation and cross-config uniqueness checks. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add typed host configs for Claude, Codex, Factory, and Kiro Extract all hardcoded host-specific values from gen-skill-docs.ts, types.ts, preamble.ts, review.ts, and setup into typed HostConfig objects. Each host is a single file in hosts/ with its paths, frontmatter rules, path/tool rewrites, runtime root manifest, and install behavior. hosts/index.ts exports all configs, derives the Host type, and provides resolveHostArg() for CLI alias handling (e.g., 'agents' -> 'codex', 'droid' -> 'factory'). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor: derive Host type and HOST_PATHS from host configs types.ts no longer hardcodes host names or paths. The Host type is derived from ALL_HOST_CONFIGS in hosts/index.ts, and HOST_PATHS is built dynamically from each config's globalRoot/localSkillRoot/usesEnvVars. Adding a new host to hosts/index.ts automatically extends the type system. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor: gen-skill-docs.ts consumes typed host configs Replace hardcoded EXTERNAL_HOST_CONFIG, transformFrontmatter host branches, path/tool rewrite if-chains, and ALL_HOSTS array with config-driven lookups from hosts/*.ts. - Host detection uses resolveHostArg() (handles aliases like agents/droid) - transformFrontmatter uses config's allowlist/denylist mode, extraFields, conditionalFields, renameFields, and descriptionLimitBehavior - Path rewrites use config's pathRewrites array (replaceAll, order matters) - Tool rewrites use config's toolRewrites object - Skill skipping uses config's generation.skipSkills - ALL_HOSTS derived from ALL_HOST_NAMES - Token budget display regex derived from host configs Golden-file comparison: all 3 hosts produce IDENTICAL output to baselines. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor: preamble, co-author trailer, and resolver suppression use host configs - preamble.ts: hostConfigDir derived from config.globalRoot instead of hardcoded Record - utility.ts: generateCoAuthorTrailer reads from config.coAuthorTrailer instead of host switch statement - gen-skill-docs.ts: suppressedResolvers from config skip resolver execution at placeholder replacement time (belt+suspenders with existing ctx.host checks in individual resolvers) Golden-file comparison: all 3 hosts produce IDENTICAL output to baselines. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: setup tooling uses config-driven host detection - host-config-export.ts: new CLI that exposes host configs to bash (list, get, detect, validate, symlinks commands) - bin/gstack-platform-detect: reads host configs instead of hardcoded binary/path mapping - scripts/skill-check.ts: iterates host configs for skill validation and freshness checks instead of separate Codex/Factory blocks - lib/worktree.ts: iterates host configs for directory copy instead of hardcoded .agents Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add OpenCode, Slate, and Cursor host configs Three new hosts added to the declarative config system. Each is a typed HostConfig object with paths, frontmatter rules, and path rewrites. All generate valid SKILL.md output with zero .claude/skills path leakage. - hosts/opencode.ts: OpenCode (opencode.ai), skills at ~/.config/opencode/ - hosts/slate.ts: Slate (Random Labs), skills at ~/.slate/ - hosts/cursor.ts: Cursor, skills at ~/.cursor/ - .gitignore: add .kiro/, .opencode/, .slate/, .cursor/, .openclaw/ Zero code changes needed — just config files + re-export in index.ts. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add OpenClaw host config with adapter for tool mapping OpenClaw gets a hybrid approach: typed config for paths/frontmatter/ detection + a post-processing adapter for semantic tool rewrites. Config handles: path rewrites, frontmatter (name+description+version), CLAUDE.md→AGENTS.md, tool name rewrites (Bash→exec, Read→read, etc.), suppressed resolvers, SOUL.md via staticFiles. Adapter handles: AskUserQuestion→prose, Agent→sessions_spawn, $B→exec $B. Zero .claude/skills path leakage. Zero hardcoded tool references remaining. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: contributor add-host skill + fix version sync - contrib/add-host/SKILL.md.tmpl: contributor-only skill that guides new host config creation. Lives in contrib/, excluded from user installs. - package.json: sync version with VERSION file (0.15.2.1) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: add parameterized host smoke tests for all hosts 35 new tests covering all 7 external hosts (Codex, Factory, Kiro, OpenCode, Slate, Cursor, OpenClaw). Each host gets 4-5 tests: - output exists on disk with SKILL.md files - no .claude/skills path leakage in non-root skills - frontmatter has name + description fields - --dry-run freshness check passes - /codex skill excluded (for hosts with skipSkills: ['codex']) Tests are parameterized over ALL_HOST_CONFIGS so adding a new host automatically gets smoke-tested with zero new test code. Also updates --host all test to verify all registered hosts generate. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: 100% coverage for host config system 71 new tests in test/host-config.test.ts covering: - hosts/index.ts: ALL_HOST_CONFIGS, getHostConfig, resolveHostArg (aliases), getExternalHosts, uniqueness checks - host-config.ts validateHostConfig: name regex, displayName, cliCommand, cliAliases, globalRoot, localSkillRoot, hostSubdir, frontmatter.mode, linkingStrategy, shell injection attempts, paths with $ and ~ - host-config.ts validateAllConfigs: duplicate name/hostSubdir/globalRoot detection, error prefix format, real configs pass - HOST_PATHS derivation: env vars for external hosts, literal paths for Claude, localSkillRoot matches config, every host has entry - host-config-export.ts CLI: list, get (string/boolean/array), detect, validate, symlinks, error cases (missing args, unknown field/host) - Golden-file regression: claude/codex/factory ship SKILL.md vs baselines - Individual host config correctness: prefixable, linkingStrategy, usesEnvVars, description limits, metadata, sidecar, tool rewrites, conditional fields, suppressed resolvers, boundary instruction, co-author trailers, skip rules, path rewrites, runtime root assets Combined with the 35 parameterized smoke tests from gen-skill-docs.test.ts, total new test coverage for multi-host: 106 tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update golden baselines and sync version after merge from main Golden files refreshed to match post-merge generated output. package.json version synced to VERSION file (0.15.4.0). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: bump version and changelog (v0.15.5.0) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: sidebar E2E tests now self-contained and passing - sidebar-url-accuracy: fix stale assertion that expected extensionUrl in prompt text (prompt format changed, URL is now in pageUrl field) - sidebar-css-interaction: simplify task from multi-step HN comment navigation to single-page example.com style injection (faster, more reliable, still exercises goto + style + completion flow) - Update golden baselines after merge from main All 3 sidebar tests now pass: 3/3, 0 fail, ~36s total. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: add ADDING_A_HOST.md guide + update docs for multi-host system - docs/ADDING_A_HOST.md: step-by-step guide for adding a new host (create config, register, gitignore, generate, test). Covers the full HostConfig interface, adapter pattern, and validation. - CONTRIBUTING.md: replace stale "Dual-host development" section with "Multi-host development" covering all 8 hosts and linking to the guide. - README.md: consolidate Codex/Factory install sections into one "Other AI Agents" section listing all supported hosts with auto-detect. - CLAUDE.md: add hosts/, host-config.ts, host-adapters/, contrib/ to project structure tree. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: README per-host install instructions for all 8 agents Each supported agent now has its own copy-paste install block with the exact command and where skills end up on disk. Includes: auto-detect, Codex, OpenCode, Cursor, Factory, OpenClaw, Slate, and Kiro. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
303 lines
9.3 KiB
TypeScript
303 lines
9.3 KiB
TypeScript
/**
|
|
* Git worktree manager for isolated test execution with change harvesting.
|
|
*
|
|
* Creates git worktrees for test suites that need real repo context,
|
|
* harvests any changes the test agent makes as patches, and provides
|
|
* deduplication across runs.
|
|
*
|
|
* Reusable platform module — future /batch or /codex challenge skills
|
|
* can import this directly.
|
|
*/
|
|
|
|
import { spawnSync } from 'child_process';
|
|
import * as crypto from 'crypto';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import * as os from 'os';
|
|
|
|
// --- Interfaces ---
|
|
|
|
export interface WorktreeInfo {
|
|
path: string;
|
|
testName: string;
|
|
originalSha: string;
|
|
createdAt: number;
|
|
}
|
|
|
|
export interface HarvestResult {
|
|
testName: string;
|
|
worktreePath: string;
|
|
diffStat: string;
|
|
patchPath: string;
|
|
changedFiles: string[];
|
|
isDuplicate: boolean;
|
|
}
|
|
|
|
// --- Utility ---
|
|
|
|
/** Recursive directory copy (pure TypeScript, no external deps). */
|
|
function copyDirSync(src: string, dest: string): void {
|
|
fs.mkdirSync(dest, { recursive: true });
|
|
for (const entry of fs.readdirSync(src, { withFileTypes: true })) {
|
|
// Skip symlinks to avoid infinite recursion (e.g., .claude/skills/gstack → repo root)
|
|
if (entry.isSymbolicLink()) continue;
|
|
const srcPath = path.join(src, entry.name);
|
|
const destPath = path.join(dest, entry.name);
|
|
if (entry.isDirectory()) {
|
|
copyDirSync(srcPath, destPath);
|
|
} else {
|
|
fs.copyFileSync(srcPath, destPath);
|
|
}
|
|
}
|
|
}
|
|
|
|
/** Run a git command and return stdout. Throws on failure unless tolerateFailure is set. */
|
|
function git(args: string[], cwd: string, tolerateFailure = false): string {
|
|
const result = spawnSync('git', args, { cwd, stdio: 'pipe', timeout: 30_000 });
|
|
const stdout = result.stdout?.toString().trim() ?? '';
|
|
const stderr = result.stderr?.toString().trim() ?? '';
|
|
if (result.status !== 0 && !tolerateFailure) {
|
|
throw new Error(`git ${args.join(' ')} failed (exit ${result.status}): ${stderr || stdout}`);
|
|
}
|
|
return stdout;
|
|
}
|
|
|
|
// --- Dedup index ---
|
|
|
|
interface DedupIndex {
|
|
hashes: Record<string, string>; // hash → first-seen runId
|
|
}
|
|
|
|
function getDedupPath(): string {
|
|
return path.join(os.homedir(), '.gstack-dev', 'harvests', 'dedup.json');
|
|
}
|
|
|
|
function loadDedupIndex(): DedupIndex {
|
|
try {
|
|
const raw = fs.readFileSync(getDedupPath(), 'utf-8');
|
|
return JSON.parse(raw);
|
|
} catch {
|
|
return { hashes: {} };
|
|
}
|
|
}
|
|
|
|
function saveDedupIndex(index: DedupIndex): void {
|
|
const dir = path.dirname(getDedupPath());
|
|
fs.mkdirSync(dir, { recursive: true });
|
|
const tmp = getDedupPath() + '.tmp';
|
|
fs.writeFileSync(tmp, JSON.stringify(index, null, 2));
|
|
fs.renameSync(tmp, getDedupPath());
|
|
}
|
|
|
|
// --- WorktreeManager ---
|
|
|
|
export class WorktreeManager {
|
|
private repoRoot: string;
|
|
private runId: string;
|
|
private active: Map<string, WorktreeInfo> = new Map();
|
|
private harvestResults: HarvestResult[] = [];
|
|
|
|
constructor(repoRoot?: string) {
|
|
if (repoRoot) {
|
|
this.repoRoot = repoRoot;
|
|
} else {
|
|
this.repoRoot = git(['rev-parse', '--show-toplevel'], process.cwd());
|
|
}
|
|
this.runId = crypto.randomUUID();
|
|
|
|
// Register cleanup on process exit
|
|
process.on('exit', () => {
|
|
this.cleanupAll();
|
|
});
|
|
}
|
|
|
|
/** Create an isolated worktree. Returns the worktree path. Throws on failure. */
|
|
create(testName: string): string {
|
|
const originalSha = git(['rev-parse', 'HEAD'], this.repoRoot);
|
|
|
|
const worktreeBase = path.join(this.repoRoot, '.gstack-worktrees', this.runId);
|
|
fs.mkdirSync(worktreeBase, { recursive: true });
|
|
|
|
const worktreePath = path.join(worktreeBase, testName);
|
|
|
|
// Create detached worktree at current HEAD
|
|
git(['worktree', 'add', '--detach', worktreePath, 'HEAD'], this.repoRoot);
|
|
|
|
// Copy gitignored build artifacts that tests need (config-driven)
|
|
const { getExternalHosts } = require('../hosts/index');
|
|
for (const hostConfig of getExternalHosts()) {
|
|
const hostSrc = path.join(this.repoRoot, hostConfig.hostSubdir);
|
|
if (fs.existsSync(hostSrc)) {
|
|
copyDirSync(hostSrc, path.join(worktreePath, hostConfig.hostSubdir));
|
|
}
|
|
}
|
|
|
|
const browseDist = path.join(this.repoRoot, 'browse', 'dist');
|
|
if (fs.existsSync(browseDist)) {
|
|
copyDirSync(browseDist, path.join(worktreePath, 'browse', 'dist'));
|
|
}
|
|
|
|
const info: WorktreeInfo = {
|
|
path: worktreePath,
|
|
testName,
|
|
originalSha,
|
|
createdAt: Date.now(),
|
|
};
|
|
this.active.set(testName, info);
|
|
|
|
return worktreePath;
|
|
}
|
|
|
|
/** Harvest changes from a worktree. Returns null if clean or on error. */
|
|
harvest(testName: string): HarvestResult | null {
|
|
const info = this.active.get(testName);
|
|
if (!info) return null;
|
|
|
|
try {
|
|
// Check if worktree directory still exists (agent may have deleted it)
|
|
if (!fs.existsSync(info.path)) {
|
|
process.stderr.write(` HARVEST [${testName}]: worktree dir deleted, skipping\n`);
|
|
return null;
|
|
}
|
|
|
|
// Stage everything including untracked files
|
|
git(['-C', info.path, 'add', '-A'], info.path, true);
|
|
|
|
// Get diff against original SHA (captures both committed and uncommitted changes)
|
|
const patch = git(['-C', info.path, 'diff', info.originalSha, '--cached'], info.path, true);
|
|
|
|
if (!patch) return null;
|
|
|
|
// Get diff stat for human-readable output
|
|
const diffStat = git(['-C', info.path, 'diff', info.originalSha, '--cached', '--stat'], info.path, true);
|
|
|
|
// Get changed file names
|
|
const nameOnly = git(['-C', info.path, 'diff', info.originalSha, '--cached', '--name-only'], info.path, true);
|
|
const changedFiles = nameOnly.split('\n').filter(Boolean);
|
|
|
|
// Dedup check
|
|
const hash = crypto.createHash('sha256').update(patch).digest('hex');
|
|
const dedupIndex = loadDedupIndex();
|
|
const isDuplicate = hash in dedupIndex.hashes;
|
|
|
|
let patchPath = '';
|
|
|
|
if (!isDuplicate) {
|
|
// Save patch
|
|
const harvestDir = path.join(os.homedir(), '.gstack-dev', 'harvests', this.runId);
|
|
fs.mkdirSync(harvestDir, { recursive: true });
|
|
patchPath = path.join(harvestDir, `${testName}.patch`);
|
|
fs.writeFileSync(patchPath, patch);
|
|
|
|
// Update dedup index
|
|
dedupIndex.hashes[hash] = this.runId;
|
|
saveDedupIndex(dedupIndex);
|
|
}
|
|
|
|
const result: HarvestResult = {
|
|
testName,
|
|
worktreePath: info.path,
|
|
diffStat,
|
|
patchPath,
|
|
changedFiles,
|
|
isDuplicate,
|
|
};
|
|
|
|
this.harvestResults.push(result);
|
|
return result;
|
|
} catch (err) {
|
|
process.stderr.write(` HARVEST [${testName}]: error — ${err}\n`);
|
|
return null;
|
|
}
|
|
}
|
|
|
|
/** Remove a worktree. Non-fatal on error. */
|
|
cleanup(testName: string): void {
|
|
const info = this.active.get(testName);
|
|
if (!info) return;
|
|
|
|
try {
|
|
git(['worktree', 'remove', '--force', info.path], this.repoRoot, true);
|
|
} catch {
|
|
// Force remove the directory if git worktree remove fails
|
|
try {
|
|
fs.rmSync(info.path, { recursive: true, force: true });
|
|
git(['worktree', 'prune'], this.repoRoot, true);
|
|
} catch { /* non-fatal */ }
|
|
}
|
|
|
|
this.active.delete(testName);
|
|
}
|
|
|
|
/** Force-remove all active worktrees (for process exit handler). */
|
|
cleanupAll(): void {
|
|
for (const testName of [...this.active.keys()]) {
|
|
this.cleanup(testName);
|
|
}
|
|
|
|
// Clean up the run directory if empty
|
|
const runDir = path.join(this.repoRoot, '.gstack-worktrees', this.runId);
|
|
try {
|
|
const entries = fs.readdirSync(runDir);
|
|
if (entries.length === 0) {
|
|
fs.rmdirSync(runDir);
|
|
}
|
|
} catch { /* non-fatal */ }
|
|
}
|
|
|
|
/** Remove worktrees from previous runs that weren't cleaned up. */
|
|
pruneStale(): void {
|
|
try {
|
|
git(['worktree', 'prune'], this.repoRoot, true);
|
|
|
|
const worktreeBase = path.join(this.repoRoot, '.gstack-worktrees');
|
|
if (!fs.existsSync(worktreeBase)) return;
|
|
|
|
for (const entry of fs.readdirSync(worktreeBase)) {
|
|
// Don't prune our own run
|
|
if (entry === this.runId) continue;
|
|
|
|
const entryPath = path.join(worktreeBase, entry);
|
|
try {
|
|
fs.rmSync(entryPath, { recursive: true, force: true });
|
|
} catch { /* non-fatal */ }
|
|
}
|
|
} catch {
|
|
process.stderr.write(' WORKTREE: prune failed (non-fatal)\n');
|
|
}
|
|
}
|
|
|
|
/** Print harvest report summary. */
|
|
printReport(): void {
|
|
if (this.harvestResults.length === 0) return;
|
|
|
|
const nonDuplicates = this.harvestResults.filter(r => !r.isDuplicate);
|
|
process.stderr.write('\n=== HARVEST REPORT ===\n');
|
|
process.stderr.write(`${nonDuplicates.length} of ${this.harvestResults.length} test suites produced new changes:\n\n`);
|
|
|
|
for (const result of this.harvestResults) {
|
|
if (result.isDuplicate) {
|
|
process.stderr.write(` ${result.testName}: duplicate patch (skipped)\n`);
|
|
} else {
|
|
process.stderr.write(` ${result.testName}: ${result.changedFiles.length} files changed\n`);
|
|
process.stderr.write(` Patch: ${result.patchPath}\n`);
|
|
process.stderr.write(` Apply: git apply ${result.patchPath}\n`);
|
|
if (result.diffStat) {
|
|
process.stderr.write(` ${result.diffStat}\n`);
|
|
}
|
|
}
|
|
process.stderr.write('\n');
|
|
}
|
|
}
|
|
|
|
/** Get the run ID (for testing). */
|
|
getRunId(): string {
|
|
return this.runId;
|
|
}
|
|
|
|
/** Get active worktree info (for testing). */
|
|
getInfo(testName: string): WorktreeInfo | undefined {
|
|
return this.active.get(testName);
|
|
}
|
|
}
|