auditor: kb_query surfaces scrum-master reviews for files in PR diff

Wires the cohesion-plan Phase C link: the scrum-master pipeline writes
per-file reviews to data/_kb/scrum_reviews.jsonl on accept; the
auditor now reads that same file and emits one kb_query finding per
scrum review whose `file` matches a path in the PR's diff.

Severity heuristic: attempt 1-3 → info, attempt 4+ → warn. Reaching
the cloud specialist (attempt 4+) means the ladder had to escalate,
which is meaningful signal reviewers should see. Tree-split fired is
also surfaced in the finding summary.

audit.ts now passes pr.files.map(f => f.path) into runKbCheck (the
old signature dropped it on the floor). Also adds auditor/audit_one.ts
— a dry-run CLI for auditing a single PR without posting to Gitea,
useful for verifying check behavior without spamming review comments.

Verified: after writing scrum_reviews for auditor/audit.ts and
mcp-server/observer.ts (both in PR #7), audit_one 7 surfaced both as
info findings with preview + accepted_model + tree_split flag. A
scrum review for playbook_memory.rs (NOT in PR #7) was correctly
filtered out.

auditor/audit.ts

@@ -52,7 +52,7 @@ export async function auditPr(pr: PrSnapshot, opts: AuditOptions = {}): Promise<
     runStaticCheck(diff),
     opts.skip_dynamic ? Promise.resolve(stubFinding("dynamic", "skipped by options")) : runDynamicCheck(),
     opts.skip_inference ? Promise.resolve(stubFinding("inference", "skipped by options")) : runInferenceCheck(claims, diff),
-    runKbCheck(claims),
+    runKbCheck(claims, pr.files.map(f => f.path)),
   ]);
 
   const allFindings: Finding[] = [

auditor/audit_one.ts

@@ -0,0 +1,68 @@
+// One-shot dry-run audit of a single PR. Useful for verifying check
+// behavior (kb_query scrum surfacing, inference prompts, etc.) without
+// posting to Gitea. Does NOT touch state.json and does NOT post
+// commit status or PR comments.
+//
+// Run: bun run auditor/audit_one.ts <pr-number>
+
+import { getPrSnapshot } from "./gitea.ts";
+import { auditPr } from "./audit.ts";
+
+async function main() {
+  const prNumRaw = process.argv[2];
+  if (!prNumRaw) {
+    console.error("usage: bun run auditor/audit_one.ts <pr-number>");
+    process.exit(2);
+  }
+  const prNum = Number(prNumRaw);
+  if (!Number.isFinite(prNum)) {
+    console.error(`invalid PR number: ${prNumRaw}`);
+    process.exit(2);
+  }
+
+  console.log(`[audit_one] fetching PR #${prNum}...`);
+  const pr = await getPrSnapshot(prNum);
+  console.log(`[audit_one] PR #${pr.number}: "${pr.title}" (head=${pr.head_sha.slice(0, 12)})`);
+  console.log(`[audit_one] files in diff: ${pr.files.length}`);
+  for (const f of pr.files) console.log(`  - ${f.path} (+${f.additions}/-${f.deletions})`);
+  console.log("");
+
+  const verdict = await auditPr(pr, {
+    dry_run: true,                      // no Gitea posting
+    skip_dynamic: true,                  // don't run fixture
+    skip_inference: process.env.LH_AUDITOR_SKIP_INFERENCE === "1",
+  });
+
+  console.log("\n═══ VERDICT ═══");
+  console.log(`overall:  ${verdict.overall}`);
+  console.log(`one-liner: ${verdict.one_liner}`);
+  console.log(`findings:  total=${verdict.metrics.findings_total} block=${verdict.metrics.findings_block} warn=${verdict.metrics.findings_warn} info=${verdict.metrics.findings_info}`);
+  console.log("");
+
+  // Print findings, highlighting kb_query scrum surfacing
+  const byCheck: Record<string, typeof verdict.findings> = {};
+  for (const f of verdict.findings) (byCheck[f.check] ||= []).push(f);
+
+  for (const [check, findings] of Object.entries(byCheck)) {
+    console.log(`── ${check} (${findings.length}) ──`);
+    for (const f of findings) {
+      const tag = f.severity === "block" ? "🛑" : f.severity === "warn" ? "⚠️ " : "ℹ️ ";
+      console.log(`  ${tag} [${f.severity}] ${f.summary}`);
+      if (f.summary.includes("scrum-master")) {
+        for (const e of f.evidence) {
+          console.log(`      → ${e.slice(0, 200)}`);
+        }
+      }
+    }
+  }
+
+  const scrumFindings = verdict.findings.filter(f => f.summary.includes("scrum-master"));
+  console.log("");
+  console.log(`═══ SCRUM WIRE CHECK: ${scrumFindings.length} scrum-master findings surfaced by kb_query ═══`);
+  if (scrumFindings.length === 0) {
+    console.log("  (none — either no matching scrum_reviews.jsonl rows, or files didn't match PR diff)");
+  }
+  process.exit(0);
+}
+
+main().catch(e => { console.error("[audit_one] fatal:", e); process.exit(1); });

auditor/checks/kb_query.ts

@@ -8,6 +8,7 @@
 // What this check reads (all file-backed, append-only or periodic):
 //   data/_kb/outcomes.jsonl         — per-scenario outcomes (kb.ts)
 //   data/_kb/error_corrections.jsonl — fail→succeed deltas on same sig
+//   data/_kb/scrum_reviews.jsonl     — scrum-master accepted reviews
 //   data/_observer/ops.jsonl         — observer ring → disk stream
 //   data/_bot/cycles/*.json          — bot cycle results
 //
@@ -21,10 +22,11 @@ import type { Claim, Finding } from "../types.ts";
 const KB_DIR = "/home/profit/lakehouse/data/_kb";
 const OBSERVER_OPS = "/home/profit/lakehouse/data/_observer/ops.jsonl";
 const BOT_CYCLES_DIR = "/home/profit/lakehouse/data/_bot/cycles";
+const SCRUM_REVIEWS_JSONL = "/home/profit/lakehouse/data/_kb/scrum_reviews.jsonl";
 const TAIL_LINES = 500;
 const MAX_BOT_CYCLE_FILES = 30;
 
-export async function runKbCheck(claims: Claim[]): Promise<Finding[]> {
+export async function runKbCheck(claims: Claim[], prFiles: string[] = []): Promise<Finding[]> {
   const findings: Finding[] = [];
 
   // 1. Recent scenario outcomes: are strong-claim-style phrases showing
@@ -48,6 +50,15 @@ export async function runKbCheck(claims: Claim[]): Promise<Finding[]> {
   const obsFindings = await checkObserverStream();
   findings.push(...obsFindings);
 
+  // 5. Scrum-master reviews — surface prior accepted reviews for any
+  //    file in this PR's diff. Cohesion plan Phase C wire: the
+  //    auditor gets to "borrow" the scrum-master's deeper per-file
+  //    analysis instead of re-doing that work.
+  if (prFiles.length > 0) {
+    const scrumFindings = await checkScrumReviews(prFiles);
+    findings.push(...scrumFindings);
+  }
+
   return findings;
 }
 
@@ -181,3 +192,54 @@ function observerBySource(ops: any[]): string {
   }
   return Object.entries(c).sort((a, b) => b[1] - a[1]).map(([k, v]) => `${k}=${v}`).join(", ") || "empty";
 }
+
+// Scrum-master reviews — the scrum pipeline writes one row per
+// accepted per-file review. We match reviews whose `file` matches
+// any path in the PR's diff, then surface the *preview* + which
+// model the escalation ladder had to reach. If the scrum-master
+// needed the 123B specialist or larger to resolve a file, that's
+// a meaningful signal about the code's complexity — and it's
+// surfaced to the PR without the auditor having to re-run the
+// escalation ladder itself.
+async function checkScrumReviews(prFiles: string[]): Promise<Finding[]> {
+  const rows = await tailJsonl<any>(SCRUM_REVIEWS_JSONL, TAIL_LINES);
+  if (rows.length === 0) return [];
+
+  // Match by exact file OR filename suffix — PR files arrive as
+  // `auditor/audit.ts`-style relative paths; scrum stores the same.
+  const norm = (p: string) => p.replace(/^\/+/, "").replace(/^home\/profit\/lakehouse\//, "");
+  const prSet = new Set(prFiles.map(norm));
+
+  // Keep only the most recent review per file (last-wins).
+  const latestByFile = new Map<string, any>();
+  for (const r of rows) {
+    const f = norm(String(r.file ?? ""));
+    if (!f) continue;
+    if (!prSet.has(f)) continue;
+    latestByFile.set(f, r);
+  }
+  if (latestByFile.size === 0) return [];
+
+  const findings: Finding[] = [];
+  for (const [file, r] of latestByFile) {
+    const model = String(r.accepted_model ?? "?");
+    const attempt = r.accepted_on_attempt ?? "?";
+    const treeSplit = !!r.tree_split_fired;
+    // Heuristic: if the scrum-master had to escalate past attempt 3,
+    // or had to tree-split, that's context the PR reviewer should see.
+    // Severity: info for low-escalation, warn if escalated far up
+    // the ladder (cloud specialist required).
+    const heavyEscalation = Number(attempt) >= 4;
+    const sev: "warn" | "info" = heavyEscalation ? "warn" : "info";
+    findings.push({
+      check: "kb_query",
+      severity: sev,
+      summary: `scrum-master review for \`${file}\` — accepted on attempt ${attempt} by \`${model}\`${treeSplit ? " (tree-split)" : ""}`,
+      evidence: [
+        `reviewed_at: ${r.reviewed_at ?? "?"}`,
+        `preview: ${String(r.suggestions_preview ?? "").slice(0, 300).replace(/\n/g, " ")}`,
+      ],
+    });
+  }
+  return findings;
+}

tests/real-world/scrum_master_pipeline.ts

@@ -27,6 +27,14 @@ const CHUNK_SIZE = 800;
 const CHUNK_OVERLAP = 120;
 const TOP_K_CONTEXT = 5;
 const MAX_ATTEMPTS = 6;
+// Files larger than this get tree-split instead of truncated. Fixes the
+// 6KB false-positive class (model claiming a field is "missing" when
+// it exists past the context cutoff).
+const FILE_TREE_SPLIT_THRESHOLD = 6000;
+const FILE_SHARD_SIZE = 3500;
+// Appended jsonl so auditor's kb_query can surface scrum findings for
+// files touched by a PR under review. Part of cohesion plan Phase C.
+const SCRUM_REVIEWS_JSONL = "/home/profit/lakehouse/data/_kb/scrum_reviews.jsonl";
 const OUT_DIR = `/home/profit/lakehouse/tests/real-world/runs/scrum_${Date.now().toString(36)}`;
 
 const PRD_PATH = "/home/profit/lakehouse/docs/PRD.md";
@@ -61,6 +69,8 @@ type Chunk = { id: string; text: string; embedding: number[]; origin: string; of
 interface FileReview {
   file: string;
   file_bytes: number;
+  tree_split_fired: boolean;
+  shards_summarized: number;
   top_prd_chunks: Array<{ origin: string; offset: number; score: number }>;
   top_proposal_chunks: Array<{ origin: string; offset: number; score: number }>;
   attempts_made: number;
@@ -153,6 +163,47 @@ function retrieveTopK(query_emb: number[], pool: Chunk[], k: number): Chunk[] {
     .map(x => ({ ...x.c, _score: x.score } as any));
 }
 
+// Tree-split a large file: shard it, summarize each shard against
+// the review question, merge into a scratchpad. Uses cloud because
+// the summarization step needs quality > speed. Returns the
+// scratchpad (full-file distillation) and the cloud-call count.
+async function treeSplitFile(
+  filePath: string,
+  content: string,
+): Promise<{ scratchpad: string; shards: number; cloud_calls: number }> {
+  const shards: Array<{ from: number; to: number; text: string }> = [];
+  for (let i = 0; i < content.length; i += FILE_SHARD_SIZE) {
+    const end = Math.min(i + FILE_SHARD_SIZE, content.length);
+    shards.push({ from: i, to: end, text: content.slice(i, end) });
+  }
+  let scratchpad = "";
+  let cloud_calls = 0;
+  log(`  tree-split: ${content.length} chars → ${shards.length} shards of ${FILE_SHARD_SIZE}`);
+  for (const [si, shard] of shards.entries()) {
+    const prompt = `You are summarizing ONE SHARD of a source file as part of a multi-shard review. File: ${filePath}. Shard ${si + 1}/${shards.length} (bytes ${shard.from}..${shard.to}).
+
+─────── shard source ───────
+${shard.text}
+─────── end shard ───────
+
+Scratchpad of prior shards (if empty, this is shard 1):
+${scratchpad || "(empty)"}
+
+Extract ONLY facts useful for reviewing this file against its PRD: function names + purposes, struct fields + types, invariants, edge cases, TODO markers, error-handling style. Under 150 words. No prose outside the extracted facts.`;
+    const r = await chat({
+      provider: "ollama_cloud",
+      model: "gpt-oss:120b",
+      prompt,
+      max_tokens: 400,
+    });
+    cloud_calls += 1;
+    if (r.content) {
+      scratchpad += `\n--- shard ${si + 1} (bytes ${shard.from}..${shard.to}) ---\n${r.content.trim()}`;
+    }
+  }
+  return { scratchpad, shards: shards.length, cloud_calls };
+}
+
 async function reviewFile(
   filePath: string,
   prd_chunks: Chunk[],
@@ -180,11 +231,39 @@ async function reviewFile(
     ...topPlan.map(c => `[PLAN @${c.offset}]\n${c.text.slice(0, 600)}`),
   ].join("\n\n");
 
+  // Files bigger than FILE_TREE_SPLIT_THRESHOLD get tree-split.
+  // Summarize each shard to a scratchpad, then review against the
+  // scratchpad instead of the truncated first chunk. Prevents the
+  // false-positive pattern where the model claims a field is
+  // "missing" because it's past the context cutoff.
+  let sourceForPrompt: string;
+  let treeSplitFired = false;
+  let shardsSummarized = 0;
+  let extraCloudCalls = 0;
+  if (content.length > FILE_TREE_SPLIT_THRESHOLD) {
+    treeSplitFired = true;
+    const ts = await treeSplitFile(rel, content);
+    shardsSummarized = ts.shards;
+    extraCloudCalls = ts.cloud_calls;
+    sourceForPrompt = `[FULL-FILE SCRATCHPAD — distilled from ${ts.shards} shards via tree-split]\n${ts.scratchpad}`;
+  } else {
+    sourceForPrompt = content;
+  }
+
+  // Prompt — when tree-split fired, include an explicit instruction
+  // not to claim a field/function is "missing" because the scratchpad
+  // is a distillation not the full file. Attacks the rubric-tuning
+  // concern J called out.
+  const truncationWarning = treeSplitFired
+    ? `\nIMPORTANT: the "source" below is a multi-shard distillation (tree-split across ${shardsSummarized} shards), NOT the full raw file. DO NOT claim any field, function, or feature is "missing" based on its absence from this distillation — the distillation may have elided it. Only call out gaps that appear DIRECTLY contradicted by the PRD excerpts.\n`
+    : "";
+
   const baseTask = `You are reviewing one source file against the Lakehouse PRD and an active cohesion-integration plan.
 
-FILE: ${rel}
+FILE: ${rel} (${content.length} bytes${treeSplitFired ? `, tree-split into ${shardsSummarized} shards` : ""})
+${truncationWarning}
 ─────── source ───────
-${content.slice(0, 6000)}${content.length > 6000 ? "\n[... truncated after 6KB ...]" : ""}
+${sourceForPrompt}
 ─────── end source ───────
 
 ${contextBlock}
@@ -234,9 +313,11 @@ Respond with markdown. Be specific, not generic. Cite file-region + PRD-chunk-of
     break;
   }
 
-  return {
+  const review: FileReview = {
     file: rel,
     file_bytes: content.length,
+    tree_split_fired: treeSplitFired,
+    shards_summarized: shardsSummarized,
     top_prd_chunks: topPrd.map(c => ({ origin: c.origin, offset: c.offset, score: (c as any)._score })),
     top_proposal_chunks: topPlan.map(c => ({ origin: c.origin, offset: c.offset, score: (c as any)._score })),
     attempts_made: history.length,
@@ -246,6 +327,31 @@ Respond with markdown. Be specific, not generic. Cite file-region + PRD-chunk-of
     suggestions: accepted ?? "[no acceptable answer after escalation ladder exhausted]",
     duration_ms: Date.now() - t0,
   };
+
+  // Append to the shared scrum-reviews jsonl so the auditor's
+  // kb_query check can surface relevant reviews for files in a
+  // PR diff. Cohesion plan Phase C wire.
+  if (accepted) {
+    const { appendFile, mkdir } = await import("node:fs/promises");
+    const { dirname } = await import("node:path");
+    await mkdir(dirname(SCRUM_REVIEWS_JSONL), { recursive: true });
+    const row = {
+      file: rel,
+      reviewed_at: new Date().toISOString(),
+      accepted_model: acceptedModel,
+      accepted_on_attempt: acceptedOn,
+      attempts_made: history.length,
+      tree_split_fired: treeSplitFired,
+      suggestions_preview: accepted.slice(0, 2000),
+    };
+    try {
+      await appendFile(SCRUM_REVIEWS_JSONL, JSON.stringify(row) + "\n");
+    } catch (e) {
+      console.error(`[scrum] failed to append scrum_reviews.jsonl: ${(e as Error).message}`);
+    }
+  }
+
+  return review;
 }
 
 async function loadAndChunk(path: string, origin_tag: string): Promise<Chunk[]> {