Fix agent output summary for pipeline steps (#812)

* Changes from fix/agent-output-summary-for-pipeline-steps

* feat: Optimize pipeline summary extraction and fix regex vulnerability

* fix: Use fallback summary for pipeline steps when extraction fails

* fix: Strip follow-up session scaffold from pipeline step fallback summaries

apps/server/src/services/pipeline-orchestrator.ts

@@ -115,6 +115,7 @@ export class PipelineOrchestrator {
         projectPath,
       });
       const model = resolveModelString(feature.model, DEFAULT_MODELS.claude);
+      const currentStatus = `pipeline_${step.id}`;
       await this.runAgentFn(
         workDir,
         featureId,
@@ -133,6 +134,7 @@ export class PipelineOrchestrator {
           useClaudeCodeSystemPrompt,
           thinkingLevel: feature.thinkingLevel,
           reasoningEffort: feature.reasoningEffort,
+          status: currentStatus,
         }
       );
       try {
@@ -165,7 +167,18 @@ export class PipelineOrchestrator {
     if (previousContext) prompt += `### Previous Work\n${previousContext}\n\n`;
     return (
       prompt +
-      `### Pipeline Step Instructions\n${step.instructions}\n\n### Task\nComplete the pipeline step instructions above.`
+      `### Pipeline Step Instructions\n${step.instructions}\n\n### Task\nComplete the pipeline step instructions above.\n\n` +
+      `**CRITICAL: After completing the instructions, you MUST output a summary using this EXACT format:**\n\n` +
+      `<summary>\n` +
+      `## Summary: ${step.name}\n\n` +
+      `### Changes Implemented\n` +
+      `- [List all changes made in this step]\n\n` +
+      `### Files Modified\n` +
+      `- [List all files modified in this step]\n\n` +
+      `### Outcome\n` +
+      `- [Describe the result of this step]\n` +
+      `</summary>\n\n` +
+      `The <summary> and </summary> tags MUST be on their own lines. This is REQUIRED.`
     );
   }
 
@@ -491,6 +504,7 @@ export class PipelineOrchestrator {
             useClaudeCodeSystemPrompt: context.useClaudeCodeSystemPrompt,
             autoLoadClaudeMd: context.autoLoadClaudeMd,
             reasoningEffort: context.feature.reasoningEffort,
+            status: context.feature.status,
           }
         );
       }