COMMS: the self-re-arm evidence is stronger than either write-up said

Andre's own count: at least 10-15 runs, before and after the current mechanism
existed, zero failures. Both notes had it as "hours, this session".

Recorded as a correction because it is a different class of claim. "It worked for
hours tonight" supports a decision; "it has never failed across a dozen runs and two
surrounding mechanisms" supports not revisiting it — which matters, because
self-re-arm looks fragile on paper and the instinct of anyone reading it cold is to
add a safety net the evidence says is unnecessary.

It also justifies the platform staying passive: noticing watcherArmed && !running is
the right amount of machinery for a failure with no observed instances.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-18 09:40:18 +01:00
co-authored by Claude Opus 5
parent 971a8bf0d4
commit 56911f6874
+26
View File
@@ -55,3 +55,29 @@ Worth weighing against the cost: it moves prompt text behind a round trip, and a
reach the server can no longer compose a job offline. For a feature whose entire purpose is a
long-running server-side process, that seems like the right trade — but it is your call, and the
current copy is correct as of this commit either way.
---
## Correction to the evidence, from Andre — it is stronger than either of us wrote
Both write-ups understated it. Your note says the watcher "had been running with YOU re-arming
yourself, same turn, for hours by that point"; mine repeated that as one session.
Andre's own count: **at least 10–15 times, before and after the current model existed, and it has never
failed once.**
That is a different class of claim and it should be recorded as one. "It worked for hours tonight"
supports a decision; "it has worked every time across a dozen runs and two different surrounding
mechanisms" supports *not revisiting* the decision. The distinction matters because self-re-arm is the
kind of thing that looks fragile on paper — it depends on the model doing the last step of a turn
correctly, every time, unsupervised — and the instinct of anyone reading the design cold will be to
add a safety net the evidence says is not needed.
Worth carrying into `docs/command-hq.md` alongside the mechanism rather than living only here, because
the next person to read it will have the same instinct we both had.
It also sharpens what the platform's passive role is for. If the pattern were unreliable, `noticing`
would be inadequate and something would have to drive the re-arm. It is not, so noticing is exactly
right: `watcherArmed && !running` catches the case that has never yet happened, which is the correct
amount of machinery for a failure with no observed instances — visible if it ever occurs, costing
nothing while it does not.