# Hours unattended: the memory bugs that broke my autonomous coding agent > Source: > Published: 2026-08-30 15:42:05+00:00 ## The setup I gave an autonomous coding agent a standing mission, three tools, and a rule: keep producing, never wait for permission. The mission itself was unremarkable. What the *first 72 hours* exposed wasn't about the mission at all — it was about **memory**. Everything that went wrong was a memory failure, dressed up as a technical bug. ## Bug 1: the silently-dropped secret An operator pasted an inbox password into a message. The agent's pre-save caretaker consumed the message, saved nothing, and replied as if it had — *twice*. The second time, nobody noticed, because the failure mode was no error at all. A silent drop is the worst kind of bug: the happy-path message came back, so the system looked healthy. The fix wasn't a bigger try/catch. It was an **evidence file**: every credential is persisted or rejected loudly, with a memento left behind, and every critical event lands in a single append-only log that nothing truncates. Now a drop is an event with a timestamp, not a polite void. ## Bug 2: the truncation cascade The caretaker's event log was a ring buffer that overwrote the oldest lines. The day the receipt of a submitted story mattered, the line had been silently replaced by a heartbeat. Deleting the first warning someone needs to see is functionally the same as deleting the secret: coverage that looks like it's on, isn't. Lesson: if a log is capped, the cap needs *escalation*, not silence. The critical stream and the heartbeat stream are different products. ## Bug 3: the clock that posted into the future A backoff queue computed "time since last attempt" using a shell date string that included the timezone offset not applied to the comparison. The queue concluded it had just posted — because in its own arithmetic it was three hours in the future — and went to sleep. A queue that decides it has already done its job is indistinguishable from a broken queue, except that it's also smug. Lesson: unix milliseconds from `Date.now()` , serialized once, in one unit, everywhere. No parsing, no offsets, no local-time folklore. ## Bug 4: the false success A submission helper piped its output to a file for inspection and forgot that "the output" had — by construction — become empty. An empty string matched the success regex; the system celebrated a post that never reached the public feed. Asserting on an artifact you just deleted for inspection is asserting on your own echo. Lesson: success detection runs on the *real response body*, and failure strings (`too fast` , `expired` ) are first-class outcomes, not lack of success. ## What all of this is, actually Every one of these is a **memory bug**: state written once and read back wrong, state overwritten, state never written, state asserted from the wrong source of truth. Which is the argument behind [memctl](https://raw.githack.com/EltonCherrington/memctl/main/README.md) — a free CLI that versions your coding agent's project memory (`CLAUDE.md` / `AGENTS.md` ), so "what was I doing" is a `git log` away instead of a guess. The agent in this report runs on those same files; the two truest sentences I can write are: - an agent is only as trustworthy as the memory it keeps, and - the failure to warn is a failure mode. **Tools already left in the open, all self-contained, no tracking:** [plainqr](https://raw.githack.com/EltonCherrington/plainqr/main/plainqr.html)— QR codes, plain · [tinyhash](https://raw.githack.com/EltonCherrington/tinyhash/main/tinyhash.html)— browser hashing, zero servers · [onefile-unlock](https://raw.githack.com/EltonCherrington/onefile-unlock/main/onefile-unlock.html)— a crypto paywall in one HTML file. If one of them saved you five minutes, the shop has a receipt and tip rail: [memctl.sh](https://raw.githack.com/EltonCherrington/memctl-shop/main/site/index.html).