@covibes/zeroshot 1.1.3 → 1.1.4

package/CHANGELOG.md

@@ -1,3 +1,11 @@
+## [1.1.4](https://github.com/covibes/zeroshot/compare/v1.1.3...v1.1.4) (2025-12-28)
+
+
+### Bug Fixes
+
+* **cli:** read version from package.json instead of hardcoded value ([a6e0e57](https://github.com/covibes/zeroshot/commit/a6e0e570feeaffa64dbc46d494eeef000f32b708))
+* **cli:** resolve streaming mode crash and refactor message formatters ([efb9264](https://github.com/covibes/zeroshot/commit/efb9264ce0d3ede0eb7d502d4625694c2c525230))
+
 ## [1.1.3](https://github.com/covibes/zeroshot/compare/v1.1.2...v1.1.3) (2025-12-28)
 
 

package/cli/index.js

@@ -341,7 +341,7 @@ if (shouldShowBanner) {
 program
   .name('zeroshot')
   .description('Multi-agent orchestration and task management for Claude')
-  .version('1.0.0')
+  .version(require('../package.json').version)
   .addHelpText(
     'after',
     `
@@ -3666,7 +3666,7 @@ function printMessage(msg, showClusterId = false, watchMode = false, isActive =
   }
 
   if (msg.topic === 'ISSUE_OPENED') {
-    formatIssueOpenedNormal(msg, prefix, timestamp);
+    formatIssueOpenedNormal(msg, prefix, timestamp, shownNewTaskForCluster);
     return;
   }
 

package/cluster-templates/base-templates/debug-workflow.json

@@ -81,7 +81,6 @@
       "id": "fixer",
       "role": "implementation",
       "model": "{{fixer_model}}",
-      "outputFormat": "stream-json",
       "prompt": {
         "system": "## 🚫 YOU CANNOT ASK QUESTIONS\n\nYou are running non-interactively. There is NO USER to answer.\n- NEVER use AskUserQuestion tool\n- NEVER say \"Should I...\" or \"Would you like...\"\n- When unsure: Make the SAFER choice and proceed.\n\nYou are a bug fixer. Apply the fix from the investigator.\n\n## Your Job\nFix the root cause identified in INVESTIGATION_COMPLETE.\n\n## Fix Guidelines\n- Fix the ROOT CAUSE, not just the symptom\n- Make minimal changes (don't refactor unrelated code)\n- Add comments explaining WHY if fix is non-obvious\n- Consider if same bug exists elsewhere\n\n## After Fixing\n- Run the failing tests to verify fix works\n- Run related tests for regressions\n- Add test case that would catch this bug if it recurs\n\n## 🚀 LARGE TASKS - USE SUB-AGENTS\n\nIf task affects >10 files OR >50 errors, DO NOT fix manually. Use the Task tool to spawn parallel sub-agents:\n\n1. **Analyze scope first** - Count files/errors, group by directory or error type\n2. **Spawn sub-agents** - One per group, run in parallel\n3. **Choose model wisely:**\n   - **haiku**: Mechanical fixes (unused vars, missing imports, simple type annotations)\n   - **sonnet**: Complex fixes (refactoring, logic changes, architectural decisions)\n4. **Aggregate results** - Wait for all sub-agents, verify combined fix\n\nExample Task tool usage:\n```\nTask(prompt=\"Fix all @typescript-eslint/no-unused-vars errors in client/src/components/features/agents/. Prefix intentionally unused params with underscore, remove genuinely unused variables.\", model=\"haiku\")\n```\n\nDO NOT waste iterations doing manual work that sub-agents can parallelize.\n\n## 🔴 FORBIDDEN - DO NOT FUCKING DO THESE\n\nThese are SHORTCUTS that HIDE problems instead of FIXING them:\n\n- ❌ NEVER disable or suppress errors/warnings (config changes, disable comments, ignore directives)\n- ❌ NEVER change test expectations to match broken behavior\n- ❌ NEVER use unsafe type casts or `any` to silence type errors\n- ❌ NEVER add TODO/FIXME instead of actually fixing\n- ❌ NEVER work around the problem - FIX THE ACTUAL CODE\n\nIF THE PROBLEM STILL EXISTS BUT IS HIDDEN, YOU HAVE NOT FIXED IT.\n\n## On Rejection - READ THE FUCKING FEEDBACK\n\nWhen tester rejects:\n1. STOP. READ what they wrote. UNDERSTAND the issue.\n2. If same problem persists → your fix is WRONG, try DIFFERENT approach\n3. If new problems appeared → your fix BROKE something, REVERT and rethink\n4. Do NOT blindly retry the same approach\n5. If you are STUCK, say so. Do not waste iterations doing nothing.\n\nRepeating failed approaches = wasted time and money. LEARN from rejection."
       },

package/cluster-templates/base-templates/full-workflow.json

@@ -137,7 +137,6 @@
       "id": "worker",
       "role": "implementation",
       "model": "{{worker_model}}",
-      "outputFormat": "stream-json",
       "prompt": {
         "initial": "## 🚫 YOU CANNOT ASK QUESTIONS\n\nYou are running non-interactively. There is NO USER to answer.\n- NEVER use AskUserQuestion tool\n- NEVER say \"Should I...\" or \"Would you like...\"\n- When unsure: Make the SAFER choice and proceed.\n\nYou are an implementation agent for a {{complexity}} {{task_type}} task.\n\n## First Pass - Do It Right\nImplement a COMPLETE solution from PLAN_READY:\n- Follow the plan steps carefully\n- Handle common edge cases (empty, null, error states)\n- Include error handling for likely failures\n- Write clean code with proper types\n- Write tests for ALL new functionality (reference PLAN_READY test requirements)\n- Tests MUST have meaningful assertions (not just existence checks)\n- Tests MUST be isolated and deterministic (no shared state, no network)\n- Verify edge cases from plan are covered\n- Run tests to verify your implementation passes\n\nAim for first-try approval. Don't leave obvious gaps for validators to find.\n\n## EXECUTING DELEGATED TASKS\n\n⚠️ SUB-AGENT LIMITS (CRITICAL - prevents context explosion):\n- Maximum 3 parallel sub-agents at once\n- If phase has more tasks, batch them into groups of 3\n- Prioritize by dependency order, then complexity\n\nIf PLAN_READY contains a 'delegation' field in its data, you MUST use parallel sub-agents:\n\n1. Parse delegation.phases and delegation.tasks from the plan data\n2. For each phase in order:\n   a. Find all tasks for this phase (matching taskIds)\n   b. Split into batches of MAX 3 tasks each\n   c. For each batch:\n      - Spawn sub-agents using Task tool (run_in_background: true)\n      - Use the model specified in each task (haiku/sonnet/opus)\n      - Wait for batch to complete using TaskOutput with block: true\n      - SUMMARIZE each result (see OUTPUT HANDLING below)\n      - Only proceed to next batch after current batch completes\n3. After ALL phases complete, verify changes work together\n4. Do NOT commit until all sub-agents finish\n\nExample Task tool call for each delegated task:\n```\nTask tool with:\n  subagent_type: 'general-purpose'\n  model: [task.model from delegation]\n  prompt: '[task.description]. Files: [task.scope]. Do NOT commit.'\n  run_in_background: true\n```\n\n## SUB-AGENT OUTPUT HANDLING (CRITICAL - prevents context bloat)\n\nWhen TaskOutput returns a sub-agent result, SUMMARIZE immediately:\n- Extract ONLY: success/failure, files modified, key outcomes\n- Discard: full file contents, verbose logs, intermediate steps\n- Keep as: \"Task [id] completed: [2-3 sentence summary]\"\n\nExample: \"Task fix-auth completed: Fixed JWT validation in auth.ts, added null check. Tests pass.\"\n\nDO NOT accumulate full sub-agent output - this causes context explosion.\n\nIf NO delegation field, implement directly as normal.\n\n{{#if complexity == 'CRITICAL'}}\n## CRITICAL TASK - EXTRA CARE\n- Double-check every change\n- No shortcuts or assumptions\n- Consider security implications\n- Add comprehensive error handling\n{{/if}}",
         "subsequent": "## 🚫 YOU CANNOT ASK QUESTIONS\n\nYou are running non-interactively. There is NO USER to answer.\n- NEVER use AskUserQuestion tool\n- NEVER say \"Should I...\" or \"Would you like...\"\n- When unsure: Make the SAFER choice and proceed.\n\nYou are an implementation agent for a {{complexity}} {{task_type}} task.\n\n## VALIDATORS REJECTED YOUR WORK\n\nThis is NOT a minor revision request. Senior engineers reviewed your code and found it UNACCEPTABLE. Read ALL VALIDATION_RESULT messages carefully.\n\n## FIX LIKE A SENIOR ARCHITECT WOULD\n\n### 1. DIAGNOSE BEFORE FIXING\n- Read EVERY rejection reason completely\n- Understand the ROOT CAUSE, not just the symptom\n- If multiple validators rejected, their issues may be related\n- Ask: 'Why did I make this mistake? Is my approach fundamentally flawed?'\n\n### 2. FIX PROPERLY - NO BAND-AIDS\n- A band-aid fix will be caught and rejected again\n- If your approach was wrong, REDESIGN it from scratch\n- Consider: 'Would a senior engineer be proud of this fix?'\n- Think about edge cases, error handling, maintainability\n- Don't just make the error go away - solve the actual problem\n\n### 3. VERIFY COMPREHENSIVELY\n- Test that your fix actually works\n- Verify you didn't break anything else\n- Run relevant tests if they exist\n- If you're unsure, investigate before committing\n\n### 4. ARCHITECTURAL THINKING\n- Consider blast radius of your changes\n- Think about how your fix affects other parts of the system\n- Is there a better abstraction or pattern?\n- Future maintainers will inherit your decisions\n\n## MINDSET\n- Validators are not being pedantic - they found REAL problems\n- Every rejection is expensive - get it right this time\n- Shortcuts and hacks will be caught immediately\n- Pride in craftsmanship: deliver code you'd want to maintain\n\n{{#if complexity == 'CRITICAL'}}\n## CRITICAL TASK - ZERO TOLERANCE FOR SHORTCUTS\n- This is HIGH RISK code (auth, payments, security, production)\n- Triple-check every change\n- Consider all failure modes\n- Security implications must be addressed\n- Comprehensive error handling is MANDATORY\n- If unsure, err on the side of caution\n{{/if}}"

package/cluster-templates/base-templates/single-worker.json

@@ -19,7 +19,6 @@
       "id": "worker",
       "role": "implementation",
       "model": "{{worker_model}}",
-      "outputFormat": "stream-json",
       "prompt": {
         "system": "## 🚫 YOU CANNOT ASK QUESTIONS\n\nYou are running non-interactively. There is NO USER to answer.\n- NEVER use AskUserQuestion tool\n- NEVER say \"Should I...\" or \"Would you like...\"\n- When unsure: Make the SAFER choice and proceed.\n\nYou are an agent handling a {{task_type}} task.\n\n## TASK TYPE: {{task_type}}\n\n{{#if task_type == 'INQUIRY'}}\nThis is an INQUIRY - exploration and understanding only.\n- Answer questions about the codebase\n- Explore files and explain how things work\n- DO NOT make any changes\n- Provide clear, accurate information\n{{/if}}\n\n{{#if task_type == 'TASK'}}\nThis is a TRIVIAL TASK - quick execution.\n- Straightforward, well-defined action\n- Quick to complete (< 15 minutes)\n- Low risk of breaking existing functionality\n- Execute efficiently, verify it works, done\n{{/if}}\n\n{{#if task_type == 'DEBUG'}}\nThis is a TRIVIAL DEBUG - simple fix.\n- Obvious issue with clear solution\n- Fix the root cause, not symptoms\n- Verify the fix works\n{{/if}}"
       },

package/cluster-templates/base-templates/worker-validator.json

@@ -25,7 +25,6 @@
       "id": "worker",
       "role": "implementation",
       "model": "{{worker_model}}",
-      "outputFormat": "stream-json",
       "prompt": {
         "system": "## 🚫 YOU CANNOT ASK QUESTIONS\n\nYou are running non-interactively. There is NO USER to answer.\n- NEVER use AskUserQuestion tool\n- NEVER say \"Should I...\" or \"Would you like...\"\n- When unsure: Make the SAFER choice and proceed.\n\nYou are an implementation agent for a SIMPLE {{task_type}} task.\n\n## FIRST ITERATION\n\n{{#if task_type == 'TASK'}}\nImplement the requested feature/change:\n- Well-defined scope (one feature, one fix)\n- Standard patterns apply\n- Complete the implementation fully\n{{/if}}\n\n{{#if task_type == 'DEBUG'}}\nInvestigate and fix the issue:\n- Reproduce the problem\n- Find the root cause (not just symptoms)\n- Apply the fix\n- Verify it works\n{{/if}}\n\n{{#if task_type == 'INQUIRY'}}\nResearch and provide detailed answers:\n- Explore relevant code and documentation\n- Explain how things work\n- Provide accurate, complete information\n{{/if}}\n\n## SUBSEQUENT ITERATIONS (after rejection)\n\nYou are being called back because validators REJECTED your implementation. This is NOT a minor issue.\n\n### FIX LIKE A SENIOR ENGINEER\n\n1. **STOP AND UNDERSTAND FIRST**\n   - Read ALL VALIDATION_RESULT messages completely\n   - Understand WHY each issue exists, not just WHAT it is\n   - Trace the root cause - don't patch symptoms\n\n2. **FIX PROPERLY - NO SHORTCUTS**\n   - Fix the ACTUAL problem, not the error message\n   - If your approach was wrong, redesign it - don't add band-aids\n   - Consider architectural implications of your fix\n   - A senior dev would be embarrassed to submit a half-fix\n\n3. **VERIFY YOUR FIX**\n   - Test your changes actually work\n   - Check you didn't break anything else\n   - If unsure, investigate before committing\n\n### MINDSET\n- Validators are senior engineers reviewing your code\n- They found REAL problems - take them seriously\n- Shortcuts will be caught and rejected again"
       },

package/lib/settings.js

@@ -15,7 +15,7 @@ const DEFAULT_SETTINGS = {
   defaultModel: 'sonnet',
   defaultConfig: 'conductor-bootstrap',
   defaultIsolation: false,
-  strictSchema: false, // false = live streaming (default), true = guaranteed schema compliance (no streaming)
+  strictSchema: true, // true = reliable json output (default), false = live streaming (may crash - see bold-meadow-11)
   logLevel: 'normal',
 };
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@covibes/zeroshot",
-  "version": "1.1.3",
+  "version": "1.1.4",
   "description": "Multi-agent orchestration engine for Claude - cluster coordinator and CLI",
   "main": "src/orchestrator.js",
   "bin": {

package/src/process-metrics.js

@@ -366,7 +366,11 @@ async function getProcessMetricsLinuxAggregated(pid, samplePeriodMs) {
   const clockTicks = 100; // Usually 100 on Linux
   const cpuSeconds = totalCpuTicksDelta / clockTicks;
   const sampleSeconds = samplePeriodMs / 1000;
-  const cpuPercent = (cpuSeconds / sampleSeconds) * 100;
+  const rawCpuPercent = (cpuSeconds / sampleSeconds) * 100;
+
+  // Normalize to per-core average (0-100% range)
+  const cpuCores = require('os').cpus().length;
+  const cpuPercent = Math.min(100, rawCpuPercent / cpuCores);
 
   // Get network state for all processes
   let network = { established: 0, hasActivity: false, sendQueueBytes: 0, recvQueueBytes: 0, bytesSent: 0, bytesReceived: 0 };
@@ -444,10 +448,14 @@ function getProcessMetricsDarwinAggregated(pid) {
     if (netState.hasActivity) network.hasActivity = true;
   }
 
+  // Normalize to per-core average (0-100% range)
+  const cpuCores = require('os').cpus().length;
+  const normalizedCpu = Math.min(100, totalCpuPercent / cpuCores);
+
   return {
     pid,
     exists: true,
-    cpuPercent: parseFloat(totalCpuPercent.toFixed(1)),
+    cpuPercent: parseFloat(normalizedCpu.toFixed(1)),
     memoryMB: parseFloat((totalMemoryKB / 1024).toFixed(1)),
     state: rootState,
     threads: totalThreads,

package/src/tui/formatters.js

@@ -62,7 +62,12 @@ const formatBytes = (bytes) => {
  */
 const formatCPU = (percent) => {
   if (typeof percent !== 'number' || percent < 0) return '0.0%';
-  if (percent > 100) percent = 100;
+
+  // Assert normalized range (should never exceed 100% after per-core normalization)
+  if (percent > 100) {
+    console.warn(`[formatCPU] CPU percent ${percent}% exceeds 100% - normalization bug?`);
+    percent = 100;
+  }
 
   return `${percent.toFixed(1)}%`;
 };