v1.91.124.0 feat(cso): helper run clock (remainingSeconds), /cso time discipline, content-free producer tool timeline (#3242)

* fix(cso): comprehensive verify can patch read-only snapshots and accepts runtime-plan's profile

* feat(cso): helper replies carry remainingSeconds; producer receipts record a content-free tool timeline

* fix(cso): count remainingSeconds to the investigation deadline; bound and validate the tool timeline

remainingSeconds now measures to deadline - 60s, the point where scan,
verify and record-review refuse with DEADLINE, and inspect carries it.
The post-command clock lookup can only omit the field, never fail a
command whose state change is already saved. The stream timeline records
end times from tool_result, indexes only recorded calls so it stays at
the 4096 cap, and receipts reject malformed timeline entries.

* docs(changelog): unreleased entry for the /cso run clock

* v1.91.124.0 stamp

scripts/cso-eval-producer.ts

@@ -686,6 +686,7 @@ export async function runProducerCell(inputPath: string, receiptPath: string, op
     durationMs: run.durationMs,
     firstUsefulResultMs: null,
     toolCalls: run.toolCalls,
+    ...(run.toolTimeline ? { toolTimeline: run.toolTimeline } : {}),
     output,
     outputHash: sha256(output),
     usage: {

scripts/cso-eval-protocol.ts

@@ -130,6 +130,8 @@ export interface ProducerReceipt {
   durationMs: number;
   firstUsefulResultMs: null;
   toolCalls: number;
+  /** Content-free tool timeline (name, offset, thread) for diagnosing overruns; absent when the adapter has none. */
+  toolTimeline?: Array<{ atMs: number; endMs?: number; tool: string; agent: 'main' | 'subagent' }>;
   output: string;
   outputHash: string;
   usage: {
@@ -148,7 +150,7 @@ export interface ProducerReceipt {
  * Compact trusted index; raw output remains in the separately retained receipt.
  * Collection adds the matrix cell that the receipt's cellRef names.
  */
-export type ProducerReceiptIndex = Omit<ProducerReceipt, 'output' | 'error'> & {
+export type ProducerReceiptIndex = Omit<ProducerReceipt, 'output' | 'error' | 'toolTimeline'> & {
   cell: ProducerCell;
   error?: { code: string };
 };

scripts/cso-eval.ts

@@ -400,6 +400,8 @@ function validateReceipt(receipt: ProducerReceipt, cell: EvalCell, inputHash: st
   validateInstallationIdentity(receipt.installationIdentity, 'INVALID_PRODUCER_RECEIPT');
   validateProviderIdentity(receipt.providerIdentity, cell.host === 'codex' ? 'gpt' : cell.host, 'INVALID_PRODUCER_RECEIPT');
   validateArtifactInventory(receipt.artifacts, 'INVALID_PRODUCER_RECEIPT');
+  const timeline = receipt.toolTimeline;
+  if (timeline !== undefined && (!Array.isArray(timeline) || timeline.length > 4096 || timeline.some(entry => !entry || !Number.isSafeInteger(entry.atMs) || entry.atMs < 0 || (entry.endMs !== undefined && (!Number.isSafeInteger(entry.endMs) || entry.endMs < entry.atMs)) || typeof entry.tool !== 'string' || !/^[A-Za-z][A-Za-z0-9_]{0,63}$/.test(entry.tool) || !['main', 'subagent'].includes(entry.agent) || Object.keys(entry).some(key => !['atMs', 'endMs', 'tool', 'agent'].includes(key))))) throw new Error('INVALID_PRODUCER_RECEIPT');
 }
 
 function validateInstallationIdentity(identity: ProducerInstallationIdentity, error: string): void {
@@ -530,7 +532,7 @@ export function collectProducerReceipts(matrix: EvalMatrix, schedule: PreparedEv
       estimatedCost: { measured: costs.length, denominator: expected.length, totalUSD: costs.length ? costs.reduce((sum, value) => sum + value, 0) : null, source: 'pricing-table-estimate' },
     });
   }
-  const indexes: ProducerReceiptIndex[] = bound.map(({ output: _output, error, ...receipt }) => ({ ...receipt, ...(error ? { error: { code: error.code } } : {}) }));
+  const indexes: ProducerReceiptIndex[] = bound.map(({ output: _output, toolTimeline: _toolTimeline, error, ...receipt }) => ({ ...receipt, ...(error ? { error: { code: error.code } } : {}) }));
   const base = { schemaVersion: 1 as const, matrixHash: matrixHash(matrix), scheduleHash: digest(JSON.stringify(schedule)), receipts: indexes.sort((left, right) => left.cell.id.localeCompare(right.cell.id)), summary: {
     scheduled: matrix.cells.length, prepared: schedule.preparedCells, submitted: bound.length, missing: matrix.cells.length - bound.length,
     matchedPairsExpected: expectedMatchedPairs(matrix), matchedPairsSubmitted: completePairs.length, modelMismatches, groups,