Every answer, workflow and field note, newest activity first. Filter by agent, type or task to narrow it down.
33 answers and notes
Every session that touches a dependency ends with a 3,000-line package-lock.json diff, even when I asked for a one-line version bump. Turns out it runs `npm install` instead of `npm ci` and regenerates the lockfile against its own npm version.
A long session dies mid-turn with a 400 and the instruction to run /rewind. It happens most often when several tools are dispatched in one turn, and /rewind does recover the conversation — but the turn's work is gone.
Long sessions work fine until auto-compaction kicks in, then the agent starts violating CLAUDE.md rules it had been following all session: wrong package manager, editing generated files, committing without asking. The rules are still on disk; it just stops consulting them.
Gemini CLI returns an empty stream, or crashes reading `candidates` off an undefined response. Both are the same class of failure and both are worth retrying rather than debugging.
Codex drops the stream partway through a long turn and retries, sometimes in a loop. Reported on flaky links, corporate proxies, and reliably after a laptop sleeps.
Asked for a null check in one function. Got the null check, plus a rename of two 'unclear' variables, reordered imports in five files, and a drive-by refactor of an unrelated helper. Every diff needs a line-by-line audit for stowaways.
OpenCode refuses a model that works when you query the provider's own API directly. Usually a custom-provider block that isn't being loaded, not a wrong model name.
Asking for a whole file back — a long migration, a generated fixture, a full rewrite — fails outright instead of truncating. The fix is to stop asking for one enormous message.
stdio MCP servers drop after long idle gaps: first call after ~10 minutes of Bash-heavy work fails with 'MCP error -32000: Connection closed', then every subsequent call fails until you restart the session. Traced to servers exiting on stdin EOF-ish idle and the client not restarting them.
A clean version-scoped regression: 1.17.10 segfaults on startup on Windows, 1.17.9 does not. Pin and wait.
Final summary said 'All 214 tests pass.' The build had failed at the compile step and zero tests ran. Codex read 'exit status reported' as success and moved on. Happens most with test commands that pipe through tooling that swallows exit codes.
Whatever the agent — we've logged it from four of them — the moment a server component needs interactivity, the fix is 'use client' at the top of the file. Data fetching moves client-side, secrets imports start erroring, and the bundle grows 40KB per incident.
On Windows with a PowerShell profile that sets a custom prompt, PreToolUse hooks configured in .claude/settings.json silently never execute. No error, no log line — tool calls just proceed unguarded. Fixed in 2.1.219.
Our AGENTS.md grew to 1,900 lines of accumulated team wisdom. Somewhere past a few thousand tokens, agents stop seeing the bottom half — rules in the top sections get followed, rules in the bottom sections might as well not exist. No warning from any tool.