fix(review): the coordinator and orchestrator texts say what the code does on refutation and the brief-conflict exception

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -536,7 +536,7 @@ Declined to Judge list, and the coordinator carries those lines into
 |------|---------|-------------|
 | **Default** | `/trekreview --project <dir>` | Claude Code `/code-review` + `/security-review`, then brief-conformance + code-correctness reviewers in parallel, coordinator dedup + verdict, write `{dir}/review.md`, verdict gate |
 | **Since ref** | `/trekreview --project <dir> --since <ref>` | Override "before" SHA for the diff range. Validated via `git rev-parse --verify` |
-| **Quick** | `/trekreview --project <dir> --quick` | `/code-review` + code-correctness reviewer only; skip brief-conformance reviewer, `/security-review` and the coordinator's reasonableness filter — fast correctness-only pass |
+| **Quick** | `/trekreview --project <dir> --quick` | `/code-review` + code-correctness reviewer only; skip brief-conformance reviewer, `/security-review` and the coordinator's reasonableness filter except the brief-conflict rule — fast correctness-only pass |
 | **Validate** | `/trekreview --project <dir> --validate` | Schema-only check on existing `review.md`. No LLM calls |
 | **Dry run** | `/trekreview --project <dir> --dry-run` | Print discovered scope + triage map; skip writes |
 | **Profile** | `/trekreview --profile <name> --project <dir>` | (v4.1.0) Pin model profile for the review phase. See [Profile system](#profile-system-v410). |

agents/review-coordinator.md

@@ -136,8 +136,9 @@ Succinctness and Actionability read the finding's *packaging*; neither
 examines the claim, so neither can establish the finding is unreal. Accuracy
 does: a citation that escapes the repo root, or a negative line, refutes the
 finding as a claim about this codebase. A line past the end of the file does
-not: the citation is wrong, the claim is unchecked. A line number alone never
-refutes a finding, so it goes to `unverified` (`accuracy:line-out-of-range`).
+not: the citation is wrong, the claim is unchecked. Any other line number alone
+never refutes the finding, so a line past the end of the file sends it to
+`unverified` (`accuracy:line-out-of-range`).
 
 **No finding is struck for length** (ordre 5). Before review_version 1.1 an
 over-long `detail` sent a finding to `unverified`, and S118's most serious

agents/review-orchestrator.md

@@ -54,8 +54,8 @@ You will receive a prompt containing:
   contract that bounds review scope.
 - **Mode** — `default`, `quick`, `validate`, or `dry-run`.
   - `default` — run the full pipeline.
-  - `quick` — skip the coordinator's reasonableness filter; use single
-    reviewer (code-correctness only) for faster turnaround.
+  - `quick` — skip the coordinator's reasonableness filter except the
+    brief-conflict rule; use single reviewer (code-correctness only) for faster turnaround.
   - `validate` — schema-only check on existing review.md, no LLM calls.
   - `dry-run` — print the discovered scope and triage map; skip writes.
 - **Since-ref** (optional) — explicit `--since <ref>` override for the SHA
@@ -191,6 +191,9 @@ The coordinator runs a 4-pass process:
    `RULE_CATALOGUE` (`unknown-rule_key`) or whose file cannot be checked
    (`file-existence:indeterminate`) to `unverified`, which forbids `ALLOW`;
    reset a severity that does not match its catalogue tier.
+   The one exception to the reset is the brief-conflict lowering: a
+   `/code-review` finding marked `contradicts_brief`, at the MAJOR tier and
+   at severity MAJOR, drops to MINOR with `brief_lowered_from: MAJOR`.
    Skipped at high effort, as in `quick` mode (below); at high effort an
    unknown `rule_key` is normalized to `PLAN_EXECUTE_DRIFT` instead
    (`agents/review-coordinator.md`, "High-effort normalization"); the

commands/trekreview.md

@@ -62,7 +62,7 @@ FLAG_SCHEMA `trekreview` entry):
 |------|------|---------|
 | `--project <dir>` | valued | Required. Path to trekplan project folder containing `brief.md`. |
 | `--since <ref>` | valued | Optional. Override "before" SHA for the diff. Validated via `git rev-parse --verify`. |
-| `--quick` | boolean | Skip the brief-conformance pass; run only the code-correctness reviewer; skip the coordinator's reasonableness filter. |
+| `--quick` | boolean | Skip the brief-conformance pass; run only the code-correctness reviewer; skip the coordinator's reasonableness filter except the brief-conflict rule. |
 | `--validate` | boolean | Schema-only check on existing `{project_dir}/review.md`. No LLM calls. |
 | `--dry-run` | boolean | Print the discovered scope and triage map. Skip writes. |
 | `--fg` | boolean | No-op alias (foreground is default). |

docs/command-modes.md

@@ -92,7 +92,7 @@ Every mode that executes refuses a plan whose approval in the approval log does
 | _(default)_ | Claude Code `/code-review` + `/security-review` (engine, via the Skill tool, never `--fix`), then brief-conformance + code-correctness reviewers in parallel, coordinator dedup + verdict, write `{project_dir}/review.md` with the required `verdict:`, decide with `lib/review/verdict-gate.mjs` (0 ALLOW/WARN · 1 BLOCK · 2 never green), propose recurring finding classes as project memory (operator approves each line) |
 | `--project <dir>` | **Required.** Path to trekplan project folder containing `brief.md`. Review is written to `{dir}/review.md` |
 | `--since <ref>` | Override "before" SHA for the diff range. Validated via `git rev-parse --verify` |
-| `--quick` | `/code-review` + code-correctness reviewer only; skip brief-conformance reviewer, `/security-review` and the coordinator's reasonableness filter — fast correctness-only pass |
+| `--quick` | `/code-review` + code-correctness reviewer only; skip brief-conformance reviewer, `/security-review` and the coordinator's reasonableness filter except the brief-conflict rule — fast correctness-only pass |
 | `--validate` | Schema-only check on existing `{dir}/review.md` plus the verdict gate. No LLM calls. A 1.0 review without `verdict:` fails here (it still seeds a plan in soft mode) |
 | `--dry-run` | Print discovered scope + triage map; skip writes |
 | `--fg` | No-op alias (foreground is default) |

tests/lib/fix-round-4-5b-prose.test.mjs

@@ -15,6 +15,14 @@
 //        no longer say "still untracked".
 //   M3   The "Back to planning" save line runs its git diff with --no-relative,
 //        so a session in a subdirectory with diff.relative on saves every file.
+//   M9   The review coordinator's Pass 2 text says what the lib does: a root
+//        escape or a negative line refutes a finding; any other line number
+//        alone never does, and a line past the end goes to `unverified`.
+//   M2   The four flag-table summaries of `--quick` (trekreview, orchestrator,
+//        command-modes, README) name the brief-conflict rule as the exception
+//        to the Pass 3 skip.
+//   K3   The orchestrator's 4-pass item 3 names the brief-conflict lowering as
+//        the exception to the catalogue reset.
 // No static import of a new export: the file must load at be0b631.
 // Fix the SOURCE a pin guards, not the pin.
 
@@ -143,3 +151,54 @@ test('[M3] the back-to-planning save line carries --no-relative', () => {
   assert.match(m[1], /^git (?:-c \S+ )*diff (?:--\S+ )*--no-relative (?:--\S+ )*\{start_sha\}$/,
     `the save line's git diff does not carry --no-relative: ${m[1]}`);
 });
+
+// --- M9 ----------------------------------------------------------------------------
+
+test('[M9] the coordinator text does not say a line number alone never refutes', () => {
+  const coord = flat(read('agents/review-coordinator.md'));
+  assert.doesNotMatch(coord, /\bA line number alone never refutes/,
+    'agents/review-coordinator.md still says a line number alone never refutes, next to a negative line that does');
+  const p2 = between('agents/review-coordinator.md', '### Pass 2 — HubSpot Judge filters', '### Pass 3 — ');
+  assert.ok(sentencesWith(p2, 'a citation that escapes the repo root, or a negative line, refutes the finding').length > 0,
+    'Pass 2 no longer says a root escape or a negative line refutes the finding');
+  const hits = sentencesWith(p2, 'line number alone never refutes');
+  assert.ok(hits.some((s) => /\b[Aa]ny other line number alone never refutes\b/.test(s)
+      && /`unverified` \(`accuracy:line-out-of-range`\)/.test(s)),
+    `no Pass 2 sentence says any other line number alone never refutes and goes to \`unverified\`: ${hits.join(' | ')}`);
+});
+
+// --- M2 ----------------------------------------------------------------------------
+
+/** The one line of `rel` that starts with `prefix` and holds `needle`. */
+function oneLine(rel, prefix, needle) {
+  const hits = read(rel).split('\n').filter((l) => l.startsWith(prefix) && l.includes(needle));
+  assert.equal(hits.length, 1, `${rel} must hold exactly one line starting "${prefix}" with "${needle}"; found ${hits.length}`);
+  return hits[0];
+}
+
+const BRIEF_CONFLICT_SKIP = /the coordinator's reasonableness filter,? except the brief-conflict rule\b/;
+
+test('[M2] each of the four flag-table summaries names the brief-conflict exception', () => {
+  const summaries = [
+    ['commands/trekreview.md --quick row', oneLine('commands/trekreview.md', '| `--quick` |', 'reasonableness filter')],
+    ['agents/review-orchestrator.md quick mode', flat(between('agents/review-orchestrator.md', '- `quick` — ', '- `validate` — '))],
+    ['docs/command-modes.md --quick row', oneLine('docs/command-modes.md', '| `--quick` |', 'reasonableness filter')],
+    ['README.md Quick row', oneLine('README.md', '| **Quick** | `/trekreview ', 'reasonableness filter')],
+  ];
+  for (const [where, text] of summaries) {
+    assert.match(text, BRIEF_CONFLICT_SKIP, `${where} skips the reasonableness filter without the brief-conflict exception: ${text}`);
+  }
+});
+
+// --- K3 ----------------------------------------------------------------------------
+
+test('[K3] orchestrator item 3 names the brief-conflict lowering as the exception to the reset', () => {
+  const item = flat(between('agents/review-orchestrator.md', '3. **Cloudflare reasonableness**', '4. **Compute verdict**'));
+  const at = item.indexOf('reset a severity that does not match its catalogue tier.');
+  assert.ok(at !== -1, `item 3 no longer resets a severity to its catalogue tier: ${item}`);
+  const next = sentencesWith(item.slice(at + 'reset a severity that does not match its catalogue tier.'.length), ' ')[0] ?? '';
+  assert.match(next, /\bexception to (the|this) reset\b/, `the sentence after the reset does not name an exception to it: ${next}`);
+  assert.match(next, /brief-conflict lowering/, `the exception to the reset is not the brief-conflict lowering: ${next}`);
+  assert.match(next, /MAJOR[^.]*\bMINOR\b/, `the exception does not say a MAJOR drops to MINOR: ${next}`);
+  assert.match(next, /`brief_lowered_from: MAJOR`/, `the exception does not name brief_lowered_from: MAJOR: ${next}`);
+});