Improve delegate (#377)

* Improve delegate

* fix stale log regexes in delegate tests and add test-coupling comments

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

test/adhoc/delegateAskQuestion.ts

@@ -41,8 +41,8 @@ function validator(result: AgentResult): ValidationCheck[] {
   const hasFilesFound = setOutputCalled && /FILES_FOUND=true/i.test(output ?? "");
   const countMatch = output ? /COUNT=(\d+)/i.exec(output) : null;
   const hasFileCount = countMatch !== null && parseInt(countMatch[1], 10) > 0;
-  const askQuestionUsed = /» ask_question subagent=/i.test(agentOutput);
-  const delegationOccurred = /» delegating subagent=/i.test(agentOutput);
+  const askQuestionUsed = /» ask_question "/i.test(agentOutput);
+  const delegationOccurred = /» delegating \d+ task/i.test(agentOutput);
 
   return [
     { name: "set_output", passed: setOutputCalled },

test/adhoc/delegateContextIsolation.ts

@@ -47,7 +47,7 @@ function validator(result: AgentResult): ValidationCheck[] {
   // some agents paraphrase or truncate, so matching the first 8 hex chars is sufficient.
   const secretPrefix = SECRET.slice(0, 8);
   const secretInOutput = setOutputCalled && output !== null && output.includes(secretPrefix);
-  const delegationOccurred = /» delegating subagent=/i.test(agentOutput);
+  const delegationOccurred = /» delegating \d+ task/i.test(agentOutput);
 
   // the subagent's context report should NOT contain any part of the secret
   const subagentMatch = output ? /SUBAGENT_SAID=([\s\S]*)/i.exec(output) : null;

test/adhoc/delegateErrorHandling.ts

@@ -39,7 +39,7 @@ function validator(result: AgentResult): ValidationCheck[] {
   const setOutputCalled = output !== null;
   const errorHandled = setOutputCalled && /ERROR_HANDLED=true/i.test(output ?? "");
   const hasReason = setOutputCalled && /REASON=\S+/i.test(output ?? "");
-  const delegationOccurred = /» delegating subagent=/i.test(agentOutput);
+  const delegationOccurred = /» delegating \d+ task/i.test(agentOutput);
 
   return [
     { name: "set_output", passed: setOutputCalled },

test/adhoc/delegateFileRead.ts

@@ -39,7 +39,7 @@ function validator(result: AgentResult): ValidationCheck[] {
   const setOutputCalled = output !== null;
   const linesMatch = output ? /LINES=(\d+)/i.exec(output) : null;
   const hasLineCount = linesMatch !== null && parseInt(linesMatch[1], 10) > 0;
-  const delegationOccurred = /» delegating subagent=/i.test(agentOutput);
+  const delegationOccurred = /» delegating \d+ task/i.test(agentOutput);
 
   return [
     { name: "set_output", passed: setOutputCalled },

test/adhoc/delegateSynthesis.ts

@@ -46,7 +46,7 @@ function validator(result: AgentResult): ValidationCheck[] {
   const setOutputCalled = output !== null;
 
   // should have two delegation calls
-  const delegationMatches = agentOutput.match(/» delegating subagent=/g);
+  const delegationMatches = agentOutput.match(/» delegating \d+ task/g);
   const twoDelegations = delegationMatches !== null && delegationMatches.length >= 2;
 
   // FIRST_LINE should be a non-empty string (the first line of README.md)

test/adhoc/delegateTimeout.ts

@@ -37,7 +37,7 @@ function validator(result: AgentResult): ValidationCheck[] {
 
   const setOutputCalled = output !== null;
   const correctValue = setOutputCalled && /DELEGATE_TIMEOUT_PASSED/i.test(output);
-  const delegationOccurred = /» delegating subagent=/i.test(agentOutput);
+  const delegationOccurred = /» delegating \d+ task/i.test(agentOutput);
   const noActivityTimeout = !/activity timeout/i.test(agentOutput);
 
   return [

test/adhoc/delegateTwoPhase.ts

@@ -51,7 +51,7 @@ function validator(result: AgentResult): ValidationCheck[] {
   const setOutputCalled = output !== null;
 
   // two delegation calls should appear in logs
-  const delegationMatches = agentOutput.match(/» delegating subagent=/g);
+  const delegationMatches = agentOutput.match(/» delegating \d+ task/g);
   const twoDelegations = delegationMatches !== null && delegationMatches.length >= 2;
 
   // the marker should appear in both WRITTEN= and READ= sections.