mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-05 05:05:08 +02:00
Merge remote-tracking branch 'origin/main' into garrytan/plan-review-regressions
This commit is contained in:
Garry Tan
@@ -13,6 +13,7 @@
|
||||
|
||||
export const ALL_MODEL_NAMES = [
|
||||
'claude',
|
||||
'opus-4-7',
|
||||
'gpt',
|
||||
'gpt-5.4',
|
||||
'gemini',
|
||||
@@ -51,6 +52,7 @@ export function resolveModel(input: string): Model | null {
|
||||
if (/^gpt-5\.4(-|$)/.test(s)) return 'gpt-5.4';
|
||||
if (/^gpt(-|$)/.test(s)) return 'gpt';
|
||||
if (/^o[0-9]+(-|$)/.test(s)) return 'o-series';
|
||||
if (/^claude-opus-4-7(-|$)/.test(s)) return 'opus-4-7';
|
||||
if (/^claude(-|$)/.test(s)) return 'claude';
|
||||
if (/^gemini(-|$)/.test(s)) return 'gemini';
|
||||
|
||||
|
||||
@@ -20,23 +20,44 @@ If A: Append this section to the end of CLAUDE.md:
|
||||
|
||||
## Skill routing
|
||||
|
||||
When the user's request matches an available skill, ALWAYS invoke it using the Skill
|
||||
tool as your FIRST action. Do NOT answer directly, do NOT use other tools first.
|
||||
The skill has specialized workflows that produce better results than ad-hoc answers.
|
||||
When the user's request matches an available skill, invoke it via the Skill tool. The
|
||||
skill has multi-step workflows, checklists, and quality gates that produce better
|
||||
results than an ad-hoc answer. When in doubt, invoke the skill. A false positive is
|
||||
cheaper than a false negative.
|
||||
|
||||
Key routing rules:
|
||||
- Product ideas, "is this worth building", brainstorming → invoke office-hours
|
||||
- Bugs, errors, "why is this broken", 500 errors → invoke investigate
|
||||
- Ship, deploy, push, create PR → invoke ship
|
||||
- QA, test the site, find bugs → invoke qa
|
||||
- Code review, check my diff → invoke review
|
||||
- Update docs after shipping → invoke document-release
|
||||
- Weekly retro → invoke retro
|
||||
- Design system, brand → invoke design-consultation
|
||||
- Visual audit, design polish → invoke design-review
|
||||
- Architecture review → invoke plan-eng-review
|
||||
- Save progress, checkpoint, resume → invoke checkpoint
|
||||
- Code quality, health check → invoke health
|
||||
- Product ideas, "is this worth building", brainstorming → invoke /office-hours
|
||||
- Strategy, scope, "think bigger", "what should we build" → invoke /plan-ceo-review
|
||||
- Architecture, "does this design make sense" → invoke /plan-eng-review
|
||||
- Design system, brand, "how should this look" → invoke /design-consultation
|
||||
- Design review of a plan → invoke /plan-design-review
|
||||
- Developer experience of a plan → invoke /plan-devex-review
|
||||
- "Review everything", full review pipeline → invoke /autoplan
|
||||
- Bugs, errors, "why is this broken", "wtf", "this doesn't work" → invoke /investigate
|
||||
- Test the site, find bugs, "does this work" → invoke /qa (or /qa-only for report only)
|
||||
- Code review, check the diff, "look at my changes" → invoke /review
|
||||
- Visual polish, design audit, "this looks off" → invoke /design-review
|
||||
- Developer experience audit, try onboarding → invoke /devex-review
|
||||
- Ship, deploy, create a PR, "send it" → invoke /ship
|
||||
- Merge + deploy + verify → invoke /land-and-deploy
|
||||
- Configure deployment → invoke /setup-deploy
|
||||
- Post-deploy monitoring → invoke /canary
|
||||
- Update docs after shipping → invoke /document-release
|
||||
- Weekly retro, "how'd we do" → invoke /retro
|
||||
- Second opinion, codex review → invoke /codex
|
||||
- Safety mode, careful mode, lock it down → invoke /careful or /guard
|
||||
- Restrict edits to a directory → invoke /freeze or /unfreeze
|
||||
- Upgrade gstack → invoke /gstack-upgrade
|
||||
- Save progress, "save my work" → invoke /context-save
|
||||
- Resume, restore, "where was I" → invoke /context-restore
|
||||
- Security audit, OWASP, "is this secure" → invoke /cso
|
||||
- Make a PDF, document, publication → invoke /make-pdf
|
||||
- Launch real browser for QA → invoke /open-gstack-browser
|
||||
- Import cookies for authenticated testing → invoke /setup-browser-cookies
|
||||
- Performance regression, page speed, benchmarks → invoke /benchmark
|
||||
- Review what gstack has learned → invoke /learn
|
||||
- Tune question sensitivity → invoke /plan-tune
|
||||
- Code quality dashboard → invoke /health
|
||||
\`\`\`
|
||||
|
||||
Then commit the change: \`git add CLAUDE.md && git commit -m "chore: add gstack skill routing rules to CLAUDE.md"\`
|
||||
@@ -46,4 +67,3 @@ Say "No problem. You can add routing rules later by running \`gstack-config set
|
||||
|
||||
This only happens once per project. If \`HAS_ROUTING\` is \`yes\` or \`ROUTING_DECLINED\` is \`true\`, skip this entirely.`;
|
||||
}
|
||||
|
||||
|
||||
@@ -55,6 +55,10 @@ Avoid filler, throat-clearing, generic optimism, founder cosplay, and unsupporte
|
||||
- Stay curious, not lecturing. "What's interesting here is..." beats "It is important to understand..."
|
||||
- End with what to do. Give the action.
|
||||
|
||||
**Example of the right voice:**
|
||||
"auth.ts:47 returns undefined when the session cookie expires. Your users hit a white screen. Fix: add a null check and redirect to /login. Two lines. Want me to fix it?"
|
||||
Not: "I've identified a potential issue in the authentication flow that may cause problems for some users under certain conditions. Let me explain the approach I'd recommend..."
|
||||
|
||||
**Final test:** does this sound like a real cross-functional builder who wants to help someone make something people want, ship it, and make it actually work?`;
|
||||
}
|
||||
|
||||
|
||||
@@ -369,7 +369,7 @@ Minimum 0 per category.
|
||||
export function generateCoAuthorTrailer(ctx: TemplateContext): string {
|
||||
const { getHostConfig } = require('../../hosts/index');
|
||||
const hostConfig = getHostConfig(ctx.host);
|
||||
return hostConfig.coAuthorTrailer || 'Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>';
|
||||
return hostConfig.coAuthorTrailer || 'Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>';
|
||||
}
|
||||
|
||||
export function generateChangelogWorkflow(_ctx: TemplateContext): string {
|
||||
|
||||
+60
-32
@@ -11,48 +11,55 @@
|
||||
* bun run slop:diff origin/release # diff against another base
|
||||
*/
|
||||
|
||||
import { spawnSync } from 'child_process';
|
||||
import * as fs from 'fs';
|
||||
import * as os from 'os';
|
||||
import * as path from 'path';
|
||||
import { spawnSync } from "child_process";
|
||||
import * as fs from "fs";
|
||||
import * as os from "os";
|
||||
import * as path from "path";
|
||||
|
||||
const base = process.argv[2] || 'main';
|
||||
const base = process.argv[2] || "main";
|
||||
|
||||
// 1. Find changed files
|
||||
const diffResult = spawnSync('git', ['diff', '--name-only', `${base}...HEAD`], {
|
||||
encoding: 'utf-8', timeout: 10000,
|
||||
const diffResult = spawnSync("git", ["diff", "--name-only", `${base}...HEAD`], {
|
||||
encoding: "utf-8",
|
||||
timeout: 10000,
|
||||
});
|
||||
const changedFiles = new Set(
|
||||
(diffResult.stdout || '').trim().split('\n').filter(Boolean)
|
||||
(diffResult.stdout || "").trim().split("\n").filter(Boolean),
|
||||
);
|
||||
if (changedFiles.size === 0) {
|
||||
console.log('No files changed vs', base, '— nothing to check.');
|
||||
console.log("No files changed vs", base, "— nothing to check.");
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
// 2. Run slop-scan on HEAD
|
||||
const scanHead = spawnSync('npx', ['slop-scan', 'scan', '.', '--json'], {
|
||||
encoding: 'utf-8', timeout: 120000, shell: true,
|
||||
const scanHead = spawnSync("npx", ["slop-scan", "scan", ".", "--json"], {
|
||||
encoding: "utf-8",
|
||||
timeout: 120000,
|
||||
shell: process.platform === "win32",
|
||||
});
|
||||
if (!scanHead.stdout) {
|
||||
console.log('slop-scan not available. Install: npm i -g slop-scan');
|
||||
console.log("slop-scan not available. Install: npm i -g slop-scan");
|
||||
process.exit(0);
|
||||
}
|
||||
let headReport: any;
|
||||
try { headReport = JSON.parse(scanHead.stdout); } catch {
|
||||
console.log('slop-scan returned invalid JSON.'); process.exit(0);
|
||||
try {
|
||||
headReport = JSON.parse(scanHead.stdout);
|
||||
} catch {
|
||||
console.log("slop-scan returned invalid JSON.");
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
// 3. Get base branch findings using git stash approach
|
||||
// Check out base versions of changed files, scan, then restore
|
||||
const mergeBase = spawnSync('git', ['merge-base', base, 'HEAD'], {
|
||||
encoding: 'utf-8', timeout: 5000,
|
||||
const mergeBase = spawnSync("git", ["merge-base", base, "HEAD"], {
|
||||
encoding: "utf-8",
|
||||
timeout: 5000,
|
||||
}).stdout?.trim();
|
||||
|
||||
// Fingerprint: strip line numbers so shifting code doesn't create false positives
|
||||
// "line 142: empty catch, boundary=none" -> "empty catch, boundary=none"
|
||||
function stripLineNum(evidence: string): string {
|
||||
return evidence.replace(/^line \d+: /, '').replace(/ at line \d+ /, ' ');
|
||||
return evidence.replace(/^line \d+: /, "").replace(/ at line \d+ /, " ");
|
||||
}
|
||||
|
||||
// Count evidence items per (rule, file, stripped-evidence) for the base
|
||||
@@ -61,27 +68,40 @@ const baseCounts = new Map<string, number>();
|
||||
if (mergeBase) {
|
||||
// Create temp worktree for base scan
|
||||
const tmpWorktree = path.join(os.tmpdir(), `slop-base-${Date.now()}`);
|
||||
const wtResult = spawnSync('git', ['worktree', 'add', '--detach', tmpWorktree, mergeBase], {
|
||||
encoding: 'utf-8', timeout: 30000,
|
||||
});
|
||||
const wtResult = spawnSync(
|
||||
"git",
|
||||
["worktree", "add", "--detach", tmpWorktree, mergeBase],
|
||||
{
|
||||
encoding: "utf-8",
|
||||
timeout: 30000,
|
||||
},
|
||||
);
|
||||
|
||||
if (wtResult.status === 0) {
|
||||
// Copy slop-scan config if it exists
|
||||
const configFile = 'slop-scan.config.json';
|
||||
const configFile = "slop-scan.config.json";
|
||||
if (fs.existsSync(configFile)) {
|
||||
try { fs.copyFileSync(configFile, path.join(tmpWorktree, configFile)); } catch {}
|
||||
try {
|
||||
fs.copyFileSync(configFile, path.join(tmpWorktree, configFile));
|
||||
} catch {}
|
||||
}
|
||||
|
||||
const scanBase = spawnSync('npx', ['slop-scan', 'scan', tmpWorktree, '--json'], {
|
||||
encoding: 'utf-8', timeout: 120000, shell: true,
|
||||
});
|
||||
const scanBase = spawnSync(
|
||||
"npx",
|
||||
["slop-scan", "scan", tmpWorktree, "--json"],
|
||||
{
|
||||
encoding: "utf-8",
|
||||
timeout: 120000,
|
||||
shell: process.platform === "win32",
|
||||
},
|
||||
);
|
||||
|
||||
if (scanBase.stdout) {
|
||||
try {
|
||||
const baseReport = JSON.parse(scanBase.stdout);
|
||||
for (const f of baseReport.findings) {
|
||||
// Remap worktree paths back to repo-relative
|
||||
const realPath = f.path.replace(tmpWorktree + '/', '');
|
||||
const realPath = f.path.replace(tmpWorktree + "/", "");
|
||||
if (!changedFiles.has(realPath)) continue;
|
||||
for (const ev of f.evidence || []) {
|
||||
const key = `${f.ruleId}|${realPath}|${stripLineNum(ev)}`;
|
||||
@@ -92,7 +112,7 @@ if (mergeBase) {
|
||||
}
|
||||
|
||||
// Clean up worktree
|
||||
spawnSync('git', ['worktree', 'remove', '--force', tmpWorktree], {
|
||||
spawnSync("git", ["worktree", "remove", "--force", tmpWorktree], {
|
||||
timeout: 10000,
|
||||
});
|
||||
}
|
||||
@@ -102,7 +122,9 @@ if (mergeBase) {
|
||||
// For each evidence item on HEAD, check if the base had the same (rule, file, stripped-evidence).
|
||||
// Use counts to handle duplicates: if base had 2 and HEAD has 3, that's 1 new.
|
||||
const headCounts = new Map<string, { count: number; evidence: string[] }>();
|
||||
const headFindings = headReport.findings.filter((f: any) => changedFiles.has(f.path));
|
||||
const headFindings = headReport.findings.filter((f: any) =>
|
||||
changedFiles.has(f.path),
|
||||
);
|
||||
|
||||
for (const f of headFindings) {
|
||||
for (const ev of f.evidence || []) {
|
||||
@@ -123,7 +145,7 @@ for (const [key, entry] of headCounts) {
|
||||
const baseCount = baseCounts.get(key) || 0;
|
||||
const netNew = entry.count - baseCount;
|
||||
if (netNew > 0) {
|
||||
const [ruleId, filePath] = key.split('|');
|
||||
const [ruleId, filePath] = key.split("|");
|
||||
// Take the last N evidence items as the "new" ones
|
||||
for (const ev of entry.evidence.slice(-netNew)) {
|
||||
newFindings.push({ ruleId, filePath, evidence: ev });
|
||||
@@ -139,14 +161,20 @@ for (const [key, baseCount] of baseCounts) {
|
||||
// 5. Print results
|
||||
if (newFindings.length === 0) {
|
||||
if (removedCount > 0) {
|
||||
console.log(`\n slop-scan: no new findings. Removed ${removedCount} pre-existing findings.\n`);
|
||||
console.log(
|
||||
`\n slop-scan: no new findings. Removed ${removedCount} pre-existing findings.\n`,
|
||||
);
|
||||
} else {
|
||||
console.log(`\n slop-scan: no new findings in ${changedFiles.size} changed files.\n`);
|
||||
console.log(
|
||||
`\n slop-scan: no new findings in ${changedFiles.size} changed files.\n`,
|
||||
);
|
||||
}
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
console.log(`\n── slop-scan: ${newFindings.length} new findings (+${newFindings.length} / -${removedCount}) ──\n`);
|
||||
console.log(
|
||||
`\n── slop-scan: ${newFindings.length} new findings (+${newFindings.length} / -${removedCount}) ──\n`,
|
||||
);
|
||||
|
||||
// Group by file, then by rule
|
||||
const grouped = new Map<string, Map<string, string[]>>();
|
||||
|
||||
Reference in New Issue
Block a user