feat(usage): count the online reviewers on each PR

README.md

@@ -1501,6 +1501,7 @@ moq-dev/quest, PRs updated and sessions active since 2026-11-06; costs (~$) esti
 #569 S merged: quest: finish model routing (quest/m0/model-routing/README)
   implementer: Claude Code, claude-opus-5-5, unknown effort
   review: Codex, gpt-6.1-sol, medium effort; round 1, score 10/10, 0 open, last round 0 fixed and 0 refuted
+  online review: review (OpenAI), not at the final head; 0 findings: 0 accepted, 0 declined, 0 unclassified, 0 unanswered
   land fixes: codex, gpt-6.1-sol, medium effort
   sessions:
      implementing  claude  claude-opus-5-5  low     in 50, cache 36.2k written 1.1M read, out 6.1k, ~$0.63
@@ -1521,12 +1522,30 @@ it or Codex marks it a review, implementing when it began before the PR opened,
 and iterating otherwise. An opencode session, whose log quest does not read, is
 the reviewing session of the newest PR whose `## Review` record names it. Each PR shows its `## Models` size and implementers; each reviewer's latest `quest review` round's
 reviewer, round, score, open findings, and the last round's findings fixed or
-refuted; the land fixer's fixes; and the later PRs that list it under
-`## Caused by`.
-
-Rollups follow: spend by size, role, harness, model, and effort, and accuracy
+refuted; the land fixer's fixes; the later PRs that list it under
+`## Caused by`; and each online reviewer's record, read from GitHub.
+
+An online reviewer is any bot account whose review has a body or opens a
+thread, as a reply-only review does not, or a review whose body opens with
+`Automated review by <name>`, as a reviewer posting under a person's account
+does. It reviewed the final head when one of its reviews with
+a body or a new thread is at the PR's last head. Its findings are the review
+threads it opens and the `[P<n>]` (or `P<n> —`) lines in its review bodies,
+one finding per title across its reviews (a repeated title in one review is
+another finding). A finding is accepted, declined, or
+unclassified by the first word of its first answer: a reply in its thread, or
+for a body finding, a PR comment that links its review or opens with an
+accepting word (`Fixed`, `Agreed`, `Applied`, `Right`, `Confirmed`,
+`Covered`, `Taken`) or a declining one (`Declined`, `Declining`, `Refuted`,
+`Not`). One with no answer counts as accepted when the reviewer settled it, by
+a bot resolving its own thread or a later review leaving it out, and as
+unanswered otherwise.
+
+Rollups follow: spend by size, role, harness, model, and effort; accuracy
 by size and implementer, where an `Implementer:` line's own size, as
-`(iterate, XS)`, counts over the PR's. Sessions on no PR here, from any
+`(iterate, XS)`, counts over the PR's; and, over the merged PRs, each online
+reviewer's coverage, final heads reviewed, findings per PR reviewed, and
+answers. Sessions on no PR here, from any
 repository or agent ccusage reads, total on an `Unattributed` line. `--pr` and
 `--quest` narrow the report to one PR or one quest's branch, and `--json`
 prints it as one object. Without `ccusage` on `PATH`, it says how to install it

quest/m0/routing-evidence/README.md

@@ -31,7 +31,7 @@ Decided 2026-11-11 (user, /quest-plan, from an audit of PRs merged
   only; none).
 - Records?
   - ✅ [Cumulative review tallies](/quest/m0/routing-evidence/review-tallies.md)
-    and [online reviewers in usage](/quest/m0/routing-evidence/online-reviewers.md)
+    and online reviewers in usage
   - ✅ [Attribution through token-max](/quest/m0/routing-evidence/usage-token-max.md),
     kept after the maintainer first left it out, because the writer A/B
     compares cost and `quest usage` crashes on this host

src/cli/main.ts

@@ -1106,9 +1106,13 @@ export function main(argv: string[], out: Output): number | Promise<number> {
 				"## Review record names it, as reviewing. Tokens and cost come from ccusage (session --json), the " +
 				"cost an estimate at each model's API list price. Each PR also shows its ## Models size and implementers, " +
 				"each reviewer's latest ## Review round, with its round, score, and findings, " +
-				"and the later PRs that list it under ## Caused by. Rollups follow: spend by size, role, harness, model, and " +
-				"effort, and accuracy by size and implementer, where an Implementer line's own size, as (iterate, XS), wins " +
-				"over the PR's. Without ccusage on PATH, it says how to install it and reports the PRs' records alone. " +
+				"the later PRs that list it under ## Caused by, and each online reviewer's record from GitHub: whether it " +
+				"reviewed the last head, and its findings accepted, declined, unclassified, or unanswered. An online reviewer " +
+				"is a bot whose review has a body or opens a thread, or a review whose body opens with Automated review by <name>; a finding is a " +
+				"review thread it opens or a [P<n>] line in its review body, and its first answer's first word takes or " +
+				"declines it. Rollups follow: spend by size, role, harness, model, and " +
+				"effort, accuracy by size and implementer, where an Implementer line's own size, as (iterate, XS), wins " +
+				"over the PR's, and each online reviewer's coverage and findings over the merged PRs. Without ccusage on PATH, it says how to install it and reports the PRs' records alone. " +
 				"--json prints the same report as one object.\n\n" +
 				"Uses GH_TOKEN, GITHUB_TOKEN, or gh auth token. Exits 0 when done, 2 for invalid arguments, and 1 for " +
 				"other failures.",