A PR driven through a dozen rounds collects a dozen "@coderabbitai
review" comments and a dozen acknowledgements, which buries the
conversation a human came to read. crq now removes its own half of that
as rounds progress, and `crq tidy` does it on demand.

Deleting a comment crq still reads is how this becomes expensive, so a
comment has to clear three guards. It belongs to a round that has
PROGRESSED — a live round keeps its command, because that is the comment
crq adopts instead of posting another. The bot acted after it, so it was
read rather than merely old. And it predates the current head, because
adoption only ever considers commands newer than the head commit; delete
one of those and the next pump posts a duplicate and buys a second
review.

Only comments crq posted. Candidates are the command IDs recorded on its
own rounds, never anything matching the text — a person's "@coderabbitai
review" is their decision to ask, not crq's to erase, and crq posts under
the same account so authorship alone cannot tell them apart.

Never the bots' own comments. An auto-generated reply can be a rate-limit
or skipped-review notice, which crq classifies as evidence and surfaces
as a finding, so deleting those would quietly destroy feedback nobody had
read yet.

A recorded command that is already gone counts as tidied rather than
failing: the bot removes some of its own command comments, and a person
may have tidied by hand.

A rate-limited round retries, and every retry posts a NEW
"@coderabbitai review" — the bot answered the previous one with the
rate-limit notice, so it can never be adopted again. crq overwrote
CommandID and forgot the old comment, which is why a throttled PR
collects a column of identical requests: nothing knew they were there,
and tidying could only ever find commands from rounds that had finished.

A round now records the commands it supersedes, bounded so a PR that
retries all day cannot grow its round without limit, and tidy treats them
as spent whichever phase the round is in. They are exempt from the
predates-the-head check on purpose: crq's own record that it has posted a
successor is stronger evidence than any timestamp.

Observed on PR #50 — five heads, nine review requests, three of them for
the first head alone. Codex is not affected: it gets one command per head
because crq skips the trigger when the bot has already reviewed it.

Adoption was the hole. A round records the command it adopted in exactly
the same CommandID as one it posted, so "the command IDs crq recorded on
its own rounds" included a person's "@coderabbitai review" — and once the
head moved on and the bot had spoken, tidy would delete it. With a
maintainer token nothing even objects.

A round now records the comments it WROTE, with the reviewer each was
addressed to and when it landed, and that list is the only candidate
source. Adopting a comment is not writing one. It also replaces the
spent-command list: a command missing from the round's current anchors is
one the round replaced, which is the same fact without a second field.

Four things fall out of carrying the reviewer with the comment:

  * a co-only round's anchor is the co-reviewer's trigger, not the
    primary's — unrelated CodeRabbit activity no longer passes for the
    answer that trigger is still waiting on, and the id stops appearing
    on the deletion list twice;
  * a superseded co-reviewer trigger is attributed to the bot that was
    asked rather than to CodeRabbit;
  * candidates are filtered against the comments actually on the PR, so
    a comment tidy already deleted is not DELETEd again on every later
    pass with the 404 read back as a fresh removal;
  * state is re-read after the observation and before the deletes, so a
    round another fleet member started in that window keeps its command.

An unreadable head commit now keeps every non-superseded command instead
of clearing the guard: the command may well be adoptable again once the
read recovers, and deleting it buys a second review. And a round that
completes while holding the slot ("cleared") or inside the reviewing
sweep is tidied — between them that is most successful rounds, so the
automatic cleanup was barely running.

…mmands