docs: the handover skill must warn that the automatic roll is broken (#489)
CI / contract (push) Successful in 1m23s
CI / build (push) Successful in 1m53s

Section 11 said the bootstrap prompt landing was 'not yet proven
end-to-end'. It is now measured failing: the first real roll joined
/clear and bootstrapText into one line. Nothing was cleared, so the
failure is safe, but a lead that reads the old wording would reach for
fleet_handover expecting it to work.

Refs fleetd #489, #480.
This commit is contained in:
Dai Ha
2026-09-12 07:21:38 +07:00
parent 7f9137fcb6
commit 2a95da2ff4
+7 -4
View File
@@ -164,10 +164,13 @@ fails.
session.
- **The roll can still refuse after `confirm` returns**, and by then there is no caller to tell.
Those outcomes are logged only, as `lead-rollover:` lines in the daemon log.
- **If the bootstrap prompt never lands, your context is gone and no fresh session starts.** This
has not yet been proven end-to-end (see fleetd #480). The recovery is the manual path: the file
is already written, so the operator starts a session and points it at the file. That is why you
write the file before you confirm, and never the other way round.
- **The bootstrap prompt does NOT land today — measured 2026-09-12, fleetd #489.** The first real
rollover joined `/clear` and the bootstrap text into one line and Claude Code refused it as
`Unknown command: /clearFresh`. The pane was never cleared and no context was lost, so the
failure is safe, but the roll does nothing. **Until #489 is merged and the daemon redeployed, use
the manual path.** The recovery is the same either way: the file is already written, so the
operator starts a session and points it at the file. That is why you write the file before you
confirm, and never the other way round.
## Writing style