mirror of https://github.com/garrytan/gstack.git synced 2026-05-02 03:35:09 +02:00

Files

T

Garry Tan c6e6a21d1a refactor: AI slop reduction with cross-model quality review (v0.16.3.0) (#941 )

* refactor: add error-handling utility module with selective catches

safeUnlink (ignores ENOENT), safeKill (ignores ESRCH), isProcessAlive
(extracted from cli.ts with Windows support), and json() Response helper.
All catches check err.code and rethrow unexpected errors instead of
swallowing silently. Unit tests cover happy path + error code paths.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: replace defensive try/catches in server.ts with utilities

Replace ~12 try/catch sites with safeUnlink/safeKill calls in shutdown,
emergencyCleanup, killAgent, and log cleanup. Convert empty catches to
selective catches with error code checks. Remove needless welcome page
try/catches (fs.existsSync doesn't need wrapping). Reduces slop-scan
empty-catch locations from 11 to 8 and error-swallowing from 24 to 18.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: extract isProcessAlive and replace try/catches in cli.ts

Move isProcessAlive to shared error-handling module. Replace ~20
try/catch sites with safeUnlink/safeKill in killServer, connect,
disconnect, and cleanup flows. Convert empty catches to selective
catches. Reduces slop-scan empty-catch from 22 to 2 locations.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: remove unnecessary return await in content-security and read-commands

Remove 6 redundant return-await patterns where there's no enclosing
try block. Eliminates all defensive.async-noise findings from these files.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: add slop-scan config to exclude vendor files

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: replace empty catches with selective error handling in sidebar-agent

Convert 8 empty catch blocks to selective catches that check err.code
(ESRCH for process kills, ENOENT for file ops). Import safeUnlink for
cancel file cleanup. Unexpected errors now propagate instead of being
silently swallowed.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: replace empty catches and mark pass-through wrappers in browser-manager

Convert 12 empty catch blocks to selective catches: filesystem ops check
ENOENT/EACCES, browser ops check for closed/Target messages, URL parsing
checks TypeError. Add 'alias for active session' comments above 6
pass-through wrapper methods to document their purpose (and exempt from
slop-scan pass-through-wrappers rule).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: selective catches in gstack-global-discover

Convert 8 defensive catch blocks to selective error handling. Filesystem
ops check ENOENT/EACCES, process ops check exit status. Unexpected errors
now propagate instead of returning silent defaults.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: selective catches in write-commands, cdp-inspector, meta-commands, snapshot

Convert ~27 empty/obscuring catches to selective error handling across 4
browse source files. CDP ops check for closed/Target/detached messages,
DOM ops check TypeError/DOMException, filesystem ops check ENOENT/EACCES,
JSON parsing checks SyntaxError. Remove dead code in cdp-inspector where
try/catch wrapped synchronous no-ops.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: selective catches in Chrome extension files

Convert empty catches and error-swallowing patterns across inspector.js,
content.js, background.js, and sidepanel.js. DOM catches filter
TypeError/DOMException, chrome API catches filter Extension context
invalidated, network catches filter Failed to fetch. Unexpected errors
now propagate.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: restore isProcessAlive boolean semantics, add safeUnlinkQuiet, remove unused json()

isProcessAlive now catches ALL errors and returns false (pure boolean
probe). Callers use it in if/while conditions without try/catch, so
throwing on EPERM was a behavior change that could crash the CLI.
Windows path gets its safety catch restored.

safeUnlinkQuiet added for best-effort cleanup paths where throwing on
non-ENOENT errors (like EPERM during shutdown) would abort cleanup.

json() removed — dead code, never imported anywhere.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use safeUnlinkQuiet in shutdown and cleanup paths

Shutdown, emergency cleanup, and disconnect paths should never throw
on file deletion failures. Switched from safeUnlink (throws on EPERM)
to safeUnlinkQuiet (swallows all errors) in these best-effort paths.
Normal operation paths (startup, lock release) keep safeUnlink.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* revert: remove brittle string-matching catches and alias comments in browser-manager

Revert 6 catches that matched error messages via includes('closed'),
includes('Target'), etc. back to empty catches. These fire-and-forget
operations (page.close, bringToFront, dialog dismiss) genuinely don't
care about any error type. String matching on error messages is brittle
and will break on Playwright version bumps.

Remove 6 'alias for active session' comments that existed solely to
game slop-scan's pass-through-wrapper exemption rule.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* revert: remove brittle string-matching catches in extension files

Revert error-swallowing fixes in background.js and sidepanel.js that
matched error messages via includes('Failed to fetch'), includes(
'Extension context invalidated'), etc. In Chrome extensions, uncaught
errors crash the entire extension. The original catch-and-log pattern
is the correct choice for extension code where any error is non-fatal.

content.js and inspector.js changes kept — their TypeError/DOMException
catches are typed, not string-based.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add slop-scan usage guidelines to CLAUDE.md

Instructions for using slop-scan to improve genuine code quality, not
to game metrics or hide that we're AI-coded. Documents what to fix
(empty catches on file/process ops, typed exception narrows, return
await) and what NOT to fix (string-matching on error messages, linter
gaming comments, tightening extension/cleanup catches). Includes
utility function reference and baseline score tracking.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: add slop-scan as diagnostic in test suite

Runs slop-scan after bun test as a non-blocking diagnostic. Prints
the summary (top files, hotspots) so you see the number without it
gating anything. Available standalone via bun run slop.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: slop-diff shows only NEW findings introduced on this branch

Runs slop-scan on HEAD and the merge-base, diffs results with
line-number-insensitive fingerprinting so shifted code doesn't create
false positives. Uses git worktree for clean base comparison. Shows
net new vs removed findings. Runs automatically after bun test.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: design doc for slop-scan integration in /review and /ship

Deferred plan for surfacing slop-diff findings automatically during
code review and shipping. Documents integration points, auto-fix vs
skip heuristics, and implementation notes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.16.3.0)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-10 17:13:15 -10:00

3.0 KiB

Raw Blame History

Design: slop-scan integration in /review and /ship

Status: deferred Created: 2026-04-09 Depends on: slop-diff script (scripts/slop-diff.ts, already landed)

Problem

slop-scan findings are only visible if you run bun run slop:diff manually. They should surface automatically during code review and shipping, the same way SQL safety and trust boundary checks do.

Integration points

/review (Step 4, after checklist pass)

Run bun run slop:diff after the critical/informational checklist pass. Show new findings inline with other review output:

Pre-Landing Review: 3 issues (1 critical, 2 informational)

AI Slop: +2 new findings, -0 removed
  browse/src/new-feature.ts
    defensive.empty-catch: 2 locations
      line 42: empty catch, boundary=filesystem
      line 87: empty catch, boundary=process

Classification: INFORMATIONAL (never blocks merge, just surfaces the pattern).

Fix-First heuristic applies: if the finding is an empty catch around a file op, auto-fix with safeUnlink(). If it's a catch-and-log in extension code, skip (that's the correct pattern per CLAUDE.md guidelines).

/ship (Step 3.5, pre-landing review + PR body)

Same integration as /review. Additionally, show a one-line summary in the PR body:

## Pre-Landing Review
- 2 issues auto-fixed, 0 needs input
- AI Slop: +0 new / -3 removed ✓

Review Readiness Dashboard

Do NOT add a row. Slop is a diagnostic on the diff, not a review that gets "run" independently. It shows up inside Eng Review output, not as its own dashboard entry.

What to auto-fix vs what to skip

Follow CLAUDE.md "Slop-scan" section. Summary:

Auto-fix (genuine quality improvements):

Empty catch around fs.unlinkSync → replace with safeUnlink()
Empty catch around process.kill → replace with safeKill()
return await with no enclosing try → remove await
Untyped catch around URL parsing → add instanceof TypeError check

Skip (correct patterns that slop-scan flags):

.catch(() => {}) on fire-and-forget browser ops (page.close, bringToFront)
Catch-and-log in Chrome extension code (uncaught errors crash extensions)
safeUnlinkQuiet in shutdown/emergency paths (swallowing all errors is correct)
Pass-through wrappers that delegate to active session (API stability layer)

Implementation notes

scripts/slop-diff.ts already handles the heavy lifting (worktree-based base comparison, line-number-insensitive fingerprinting, graceful fallback)
The review/ship skills run bash blocks. Integration is: run the script, parse the output, include in the review findings
If slop-scan is not installed (npx slop-scan fails), skip silently
The script exits 0 always (diagnostic, never gates)

Effort estimate

Task	Human	CC+gstack
Add to review/SKILL.md.tmpl	2 hours	10 min
Add to ship/SKILL.md.tmpl	2 hours	10 min
Add to review/checklist.md	1 hour	5 min
Test with actual PRs	2 hours	15 min
Regenerate SKILL.md files	—	1 min

3.0 KiB Raw Blame History