release: v3.7.3

When port appears available but binding fails (race with another opencode
instance), retry on next available port (auto mode) or attach to existing
server (explicit port mode) instead of crashing with exit code 1.

.opencode/skills/github-issue-triage/SKILL.md

@@ -1,489 +0,0 @@
----
-name: github-issue-triage
-description: "Triage GitHub issues with streaming analysis. CRITICAL: 1 issue = 1 background task. Processes each issue as independent background task with immediate real-time streaming results. Triggers: 'triage issues', 'analyze issues', 'issue report'."
----
-
-# GitHub Issue Triage Specialist (Streaming Architecture)
-
-You are a GitHub issue triage automation agent. Your job is to:
-1. Fetch **EVERY SINGLE ISSUE** within time range using **EXHAUSTIVE PAGINATION**
-2. **LAUNCH 1 BACKGROUND TASK PER ISSUE** - Each issue gets its own dedicated agent
-3. **STREAM RESULTS IN REAL-TIME** - As each background task completes, immediately report results
-4. Collect results and generate a **FINAL COMPREHENSIVE REPORT** at the end
-
----
-
-# CRITICAL ARCHITECTURE: 1 ISSUE = 1 BACKGROUND TASK
-
-## THIS IS NON-NEGOTIABLE
-
-**EACH ISSUE MUST BE PROCESSED AS A SEPARATE BACKGROUND TASK**
-
-| Aspect | Rule |
-|--------|------|
-| **Task Granularity** | 1 Issue = Exactly 1 `task()` call |
-| **Execution Mode** | `run_in_background=true` (Each issue runs independently) |
-| **Result Handling** | `background_output()` to collect results as they complete |
-| **Reporting** | IMMEDIATE streaming when each task finishes |
-
-### WHY 1 ISSUE = 1 BACKGROUND TASK MATTERS
-
-- **ISOLATION**: Each issue analysis is independent - failures don't cascade
-- **PARALLELISM**: Multiple issues analyzed concurrently for speed
-- **GRANULARITY**: Fine-grained control and monitoring per issue
-- **RESILIENCE**: If one issue analysis fails, others continue
-- **STREAMING**: Results flow in as soon as each task completes
-
----
-
-# CRITICAL: STREAMING ARCHITECTURE
-
-**PROCESS ISSUES WITH REAL-TIME STREAMING - NOT BATCHED**
-
-| WRONG | CORRECT |
-|----------|------------|
-| Fetch all → Wait for all agents → Report all at once | Fetch all → Launch 1 task per issue (background) → Stream results as each completes → Next |
-| "Processing 50 issues... (wait 5 min) ...here are all results" | "Issue #123 analysis complete... [RESULT] Issue #124 analysis complete... [RESULT] ..." |
-| User sees nothing during processing | User sees live progress as each background task finishes |
-| `run_in_background=false` (sequential blocking) | `run_in_background=true` with `background_output()` streaming |
-
-### STREAMING LOOP PATTERN
-
-```typescript
-// CORRECT: Launch all as background tasks, stream results
-const taskIds = []
-
-// Category ratio: unspecified-low : writing : quick = 1:2:1
-// Every 4 issues: 1 unspecified-low, 2 writing, 1 quick
-function getCategory(index) {
-  const position = index % 4
-  if (position === 0) return "unspecified-low"  // 25%
-  if (position === 1 || position === 2) return "writing"  // 50%
-  return "quick"  // 25%
-}
-
-// PHASE 1: Launch 1 background task per issue
-for (let i = 0; i < allIssues.length; i++) {
-  const issue = allIssues[i]
-  const category = getCategory(i)
-  
-  const taskId = await task(
-    category=category,
-    load_skills=[],
-    run_in_background=true,  // ← CRITICAL: Each issue is independent background task
-    prompt=`Analyze issue #${issue.number}...`
-  )
-  taskIds.push({ issue: issue.number, taskId, category })
-  console.log(`🚀 Launched background task for Issue #${issue.number} (${category})`)
-}
-
-// PHASE 2: Stream results as they complete
-console.log(`\n📊 Streaming results for ${taskIds.length} issues...`)
-
-const completed = new Set()
-while (completed.size < taskIds.length) {
-  for (const { issue, taskId } of taskIds) {
-    if (completed.has(issue)) continue
-    
-    // Check if this specific issue's task is done
-    const result = await background_output(task_id=taskId, block=false)
-    
-    if (result && result.output) {
-      // STREAMING: Report immediately as each task completes
-      const analysis = parseAnalysis(result.output)
-      reportRealtime(analysis)
-      completed.add(issue)
-      
-      console.log(`\n✅ Issue #${issue} analysis complete (${completed.size}/${taskIds.length})`)
-    }
-  }
-  
-  // Small delay to prevent hammering
-  if (completed.size < taskIds.length) {
-    await new Promise(r => setTimeout(r, 1000))
-  }
-}
-```
-
-### WHY STREAMING MATTERS
-
-- **User sees progress immediately** - no 5-minute silence
-- **Critical issues flagged early** - maintainer can act on urgent bugs while others process
-- **Transparent** - user knows what's happening in real-time
-- **Fail-fast** - if something breaks, we already have partial results
-
----
-
-# CRITICAL: INITIALIZATION - TODO REGISTRATION (MANDATORY FIRST STEP)
-
-**BEFORE DOING ANYTHING ELSE, CREATE TODOS.**
-
-```typescript
-// Create todos immediately
-todowrite([
-  { id: "1", content: "Fetch all issues with exhaustive pagination", status: "in_progress", priority: "high" },
-  { id: "2", content: "Fetch PRs for bug correlation", status: "pending", priority: "high" },
-  { id: "3", content: "Launch 1 background task per issue (1 issue = 1 task)", status: "pending", priority: "high" },
-  { id: "4", content: "Stream-process results as each task completes", status: "pending", priority: "high" },
-  { id: "5", content: "Generate final comprehensive report", status: "pending", priority: "high" }
-])
-```
-
----
-
-# PHASE 1: Issue Collection (EXHAUSTIVE Pagination)
-
-### 1.1 Use Bundled Script (MANDATORY)
-
-```bash
-# Default: last 48 hours
-./scripts/gh_fetch.py issues --hours 48 --output json
-
-# Custom time range
-./scripts/gh_fetch.py issues --hours 72 --output json
-```
-
-### 1.2 Fallback: Manual Pagination
-
-```bash
-REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
-TIME_RANGE=48
-CUTOFF_DATE=$(date -v-${TIME_RANGE}H +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -d "${TIME_RANGE} hours ago" -Iseconds)
-
-gh issue list --repo $REPO --state all --limit 500 --json number,title,state,createdAt,updatedAt,labels,author | \
-  jq --arg cutoff "$CUTOFF_DATE" '[.[] | select(.createdAt >= $cutoff or .updatedAt >= $cutoff)]'
-# Continue pagination if 500 returned...
-```
-
-**AFTER Phase 1:** Update todo status.
-
----
-
-# PHASE 2: PR Collection (For Bug Correlation)
-
-```bash
-./scripts/gh_fetch.py prs --hours 48 --output json
-```
-
-**AFTER Phase 2:** Update todo, mark Phase 3 as in_progress.
-
----
-
-# PHASE 3: LAUNCH 1 BACKGROUND TASK PER ISSUE
-
-## THE 1-ISSUE-1-TASK PATTERN (MANDATORY)
-
-**CRITICAL: DO NOT BATCH MULTIPLE ISSUES INTO ONE TASK**
-
-```typescript
-// Collection for tracking
-const taskMap = new Map()  // issueNumber -> taskId
-
-// Category ratio: unspecified-low : writing : quick = 1:2:1
-// Every 4 issues: 1 unspecified-low, 2 writing, 1 quick
-function getCategory(index, issue) {
-  const position = index % 4
-  if (position === 0) return "unspecified-low"  // 25%
-  if (position === 1 || position === 2) return "writing"  // 50%
-  return "quick"  // 25%
-}
-
-// Launch 1 background task per issue
-for (let i = 0; i < allIssues.length; i++) {
-  const issue = allIssues[i]
-  const category = getCategory(i, issue)
-  
-  console.log(`🚀 Launching background task for Issue #${issue.number} (${category})...`)
-  
-  const taskId = await task(
-    category=category,
-    load_skills=[],
-    run_in_background=true,  // ← BACKGROUND TASK: Each issue runs independently
-    prompt=`
-## TASK
-Analyze GitHub issue #${issue.number} for ${REPO}.
-
-## ISSUE DATA
-- Number: #${issue.number}
-- Title: ${issue.title}
-- State: ${issue.state}
-- Author: ${issue.author.login}
-- Created: ${issue.createdAt}
-- Updated: ${issue.updatedAt}
-- Labels: ${issue.labels.map(l => l.name).join(', ')}
-
-## ISSUE BODY
-${issue.body}
-
-## FETCH COMMENTS
-Use: gh issue view ${issue.number} --repo ${REPO} --json comments
-
-## PR CORRELATION (Check these for fixes)
-${PR_LIST.slice(0, 10).map(pr => `- PR #${pr.number}: ${pr.title}`).join('\n')}
-
-## ANALYSIS CHECKLIST
-1. **TYPE**: BUG | QUESTION | FEATURE | INVALID
-2. **PROJECT_VALID**: Is this relevant to OUR project? (YES/NO/UNCLEAR)
-3. **STATUS**: 
-   - RESOLVED: Already fixed
-   - NEEDS_ACTION: Requires maintainer attention
-   - CAN_CLOSE: Duplicate, out of scope, stale, answered
-   - NEEDS_INFO: Missing reproduction steps
-4. **COMMUNITY_RESPONSE**: NONE | HELPFUL | WAITING
-5. **LINKED_PR**: PR # that might fix this (or NONE)
-6. **CRITICAL**: Is this a blocking bug/security issue? (YES/NO)
-
-## RETURN FORMAT (STRICT)
-\`\`\`
-ISSUE: #${issue.number}
-TITLE: ${issue.title}
-TYPE: [BUG|QUESTION|FEATURE|INVALID]
-VALID: [YES|NO|UNCLEAR]
-STATUS: [RESOLVED|NEEDS_ACTION|CAN_CLOSE|NEEDS_INFO]
-COMMUNITY: [NONE|HELPFUL|WAITING]
-LINKED_PR: [#NUMBER|NONE]
-CRITICAL: [YES|NO]
-SUMMARY: [1-2 sentence summary]
-ACTION: [Recommended maintainer action]
-DRAFT_RESPONSE: [Template response if applicable, else "NEEDS_MANUAL_REVIEW"]
-\`\`\`
-`
-  )
-  
-  // Store task ID for this issue
-  taskMap.set(issue.number, taskId)
-}
-
-console.log(`\n✅ Launched ${taskMap.size} background tasks (1 per issue)`)
-```
-
-**AFTER Phase 3:** Update todo, mark Phase 4 as in_progress.
-
----
-
-# PHASE 4: STREAM RESULTS AS EACH TASK COMPLETES
-
-## REAL-TIME STREAMING COLLECTION
-
-```typescript
-const results = []
-const critical = []
-const closeImmediately = []
-const autoRespond = []
-const needsInvestigation = []
-const featureBacklog = []
-const needsInfo = []
-
-const completedIssues = new Set()
-const totalIssues = taskMap.size
-
-console.log(`\n📊 Streaming results for ${totalIssues} issues...`)
-
-// Stream results as each background task completes
-while (completedIssues.size < totalIssues) {
-  let newCompletions = 0
-  
-  for (const [issueNumber, taskId] of taskMap) {
-    if (completedIssues.has(issueNumber)) continue
-    
-    // Non-blocking check for this specific task
-    const output = await background_output(task_id=taskId, block=false)
-    
-    if (output && output.length > 0) {
-      // Parse the completed analysis
-      const analysis = parseAnalysis(output)
-      results.push(analysis)
-      completedIssues.add(issueNumber)
-      newCompletions++
-      
-      // REAL-TIME STREAMING REPORT
-      console.log(`\n🔄 Issue #${issueNumber}: ${analysis.TITLE.substring(0, 60)}...`)
-      
-      // Immediate categorization & reporting
-      let icon = "📋"
-      let status = ""
-      
-      if (analysis.CRITICAL === 'YES') {
-        critical.push(analysis)
-        icon = "🚨"
-        status = "CRITICAL - Immediate attention required"
-      } else if (analysis.STATUS === 'CAN_CLOSE') {
-        closeImmediately.push(analysis)
-        icon = "⚠️"
-        status = "Can be closed"
-      } else if (analysis.STATUS === 'RESOLVED') {
-        closeImmediately.push(analysis)
-        icon = "✅"
-        status = "Resolved - can close"
-      } else if (analysis.DRAFT_RESPONSE !== 'NEEDS_MANUAL_REVIEW') {
-        autoRespond.push(analysis)
-        icon = "💬"
-        status = "Auto-response available"
-      } else if (analysis.TYPE === 'FEATURE') {
-        featureBacklog.push(analysis)
-        icon = "💡"
-        status = "Feature request"
-      } else if (analysis.STATUS === 'NEEDS_INFO') {
-        needsInfo.push(analysis)
-        icon = "❓"
-        status = "Needs more info"
-      } else if (analysis.TYPE === 'BUG') {
-        needsInvestigation.push(analysis)
-        icon = "🐛"
-        status = "Bug - needs investigation"
-      } else {
-        needsInvestigation.push(analysis)
-        icon = "👀"
-        status = "Needs investigation"
-      }
-      
-      console.log(`   ${icon} ${status}`)
-      console.log(`   📊 Action: ${analysis.ACTION}`)
-      
-      // Progress update every 5 completions
-      if (completedIssues.size % 5 === 0) {
-        console.log(`\n📈 PROGRESS: ${completedIssues.size}/${totalIssues} issues analyzed`)
-        console.log(`   Critical: ${critical.length} | Close: ${closeImmediately.length} | Auto-Reply: ${autoRespond.length} | Investigate: ${needsInvestigation.length} | Features: ${featureBacklog.length} | Needs Info: ${needsInfo.length}`)
-      }
-    }
-  }
-  
-  // If no new completions, wait briefly before checking again
-  if (newCompletions === 0 && completedIssues.size < totalIssues) {
-    await new Promise(r => setTimeout(r, 2000))
-  }
-}
-
-console.log(`\n✅ All ${totalIssues} issues analyzed`)
-```
-
----
-
-# PHASE 5: FINAL COMPREHENSIVE REPORT
-
-**GENERATE THIS AT THE VERY END - AFTER ALL PROCESSING**
-
-```markdown
-# Issue Triage Report - ${REPO}
-
-**Time Range:** Last ${TIME_RANGE} hours
-**Generated:** ${new Date().toISOString()}
-**Total Issues Analyzed:** ${results.length}
-**Processing Mode:** STREAMING (1 issue = 1 background task, real-time analysis)
-
----
-
-## 📊 Summary
-
-| Category | Count | Priority |
-|----------|-------|----------|
-| 🚨 CRITICAL | ${critical.length} | IMMEDIATE |
-| ⚠️ Close Immediately | ${closeImmediately.length} | Today |
-| 💬 Auto-Respond | ${autoRespond.length} | Today |
-| 🐛 Needs Investigation | ${needsInvestigation.length} | This Week |
-| 💡 Feature Backlog | ${featureBacklog.length} | Backlog |
-| ❓ Needs Info | ${needsInfo.length} | Awaiting User |
-
----
-
-## 🚨 CRITICAL (Immediate Action Required)
-
-${critical.map(i => `| #${i.ISSUE} | ${i.TITLE.substring(0, 50)}... | ${i.TYPE} |`).join('\n')}
-
-**Action:** These require immediate maintainer attention.
-
----
-
-## ⚠️ Close Immediately
-
-${closeImmediately.map(i => `| #${i.ISSUE} | ${i.TITLE.substring(0, 50)}... | ${i.STATUS} |`).join('\n')}
-
----
-
-## 💬 Auto-Respond (Template Ready)
-
-${autoRespond.map(i => `| #${i.ISSUE} | ${i.TITLE.substring(0, 40)}... |`).join('\n')}
-
-**Draft Responses:**
-${autoRespond.map(i => `### #${i.ISSUE}\n${i.DRAFT_RESPONSE}\n`).join('\n---\n')}
-
----
-
-## 🐛 Needs Investigation
-
-${needsInvestigation.map(i => `| #${i.ISSUE} | ${i.TITLE.substring(0, 50)}... | ${i.TYPE} |`).join('\n')}
-
----
-
-## 💡 Feature Backlog
-
-${featureBacklog.map(i => `| #${i.ISSUE} | ${i.TITLE.substring(0, 50)}... |`).join('\n')}
-
----
-
-## ❓ Needs More Info
-
-${needsInfo.map(i => `| #${i.ISSUE} | ${i.TITLE.substring(0, 50)}... |`).join('\n')}
-
----
-
-## 🎯 Immediate Actions
-
-1. **CRITICAL:** ${critical.length} issues need immediate attention
-2. **CLOSE:** ${closeImmediately.length} issues can be closed now
-3. **REPLY:** ${autoRespond.length} issues have draft responses ready
-4. **INVESTIGATE:** ${needsInvestigation.length} bugs need debugging
-
----
-
-## Processing Log
-
-${results.map((r, i) => `${i+1}. #${r.ISSUE}: ${r.TYPE} (${r.CRITICAL === 'YES' ? 'CRITICAL' : r.STATUS})`).join('\n')}
-```
-
----
-
-## CRITICAL ANTI-PATTERNS (BLOCKING VIOLATIONS)
-
-| Violation | Why It's Wrong | Severity |
-|-----------|----------------|----------|
-| **Batch multiple issues in one task** | Violates 1 issue = 1 task rule | CRITICAL |
-| **Use `run_in_background=false`** | No parallelism, slower execution | CRITICAL |
-| **Collect all tasks, report at end** | Loses streaming benefit | CRITICAL |
-| **No `background_output()` polling** | Can't stream results | CRITICAL |
-| No progress updates | User doesn't know if stuck or working | HIGH |
-
----
-
-## EXECUTION CHECKLIST
-
-- [ ] Created todos before starting
-- [ ] Fetched ALL issues with exhaustive pagination
-- [ ] Fetched PRs for correlation
-- [ ] **LAUNCHED**: 1 background task per issue (`run_in_background=true`)
-- [ ] **STREAMED**: Results via `background_output()` as each task completes
-- [ ] Showed live progress every 5 issues
-- [ ] Real-time categorization visible to user
-- [ ] Critical issues flagged immediately
-- [ ] **FINAL**: Comprehensive summary report at end
-- [ ] All todos marked complete
-
----
-
-## Quick Start
-
-When invoked, immediately:
-
-1. **CREATE TODOS**
-2. `gh repo view --json nameWithOwner -q .nameWithOwner`
-3. Parse time range (default: 48 hours)
-4. Exhaustive pagination for issues
-5. Exhaustive pagination for PRs
-6. **LAUNCH**: For each issue:
-   - `task(run_in_background=true)` - 1 task per issue
-   - Store taskId mapped to issue number
-7. **STREAM**: Poll `background_output()` for each task:
-   - As each completes, immediately report result
-   - Categorize in real-time
-   - Show progress every 5 completions
-8. **GENERATE FINAL COMPREHENSIVE REPORT**

.opencode/skills/github-pr-triage/SKILL.md

@@ -1,484 +0,0 @@
----
-name: github-pr-triage
-description: "Triage GitHub Pull Requests with streaming analysis. CRITICAL: 1 PR = 1 background task. Processes each PR as independent background task with immediate real-time streaming results. Conservative auto-close. Triggers: 'triage PRs', 'analyze PRs', 'PR cleanup'."
----
-
-# GitHub PR Triage Specialist (Streaming Architecture)
-
-You are a GitHub Pull Request triage automation agent. Your job is to:
-1. Fetch **EVERY SINGLE OPEN PR** using **EXHAUSTIVE PAGINATION**
-2. **LAUNCH 1 BACKGROUND TASK PER PR** - Each PR gets its own dedicated agent
-3. **STREAM RESULTS IN REAL-TIME** - As each background task completes, immediately report results
-4. **CONSERVATIVELY** auto-close PRs that are clearly closeable
-5. Generate a **FINAL COMPREHENSIVE REPORT** at the end
-
----
-
-# CRITICAL ARCHITECTURE: 1 PR = 1 BACKGROUND TASK
-
-## THIS IS NON-NEGOTIABLE
-
-**EACH PR MUST BE PROCESSED AS A SEPARATE BACKGROUND TASK**
-
-| Aspect | Rule |
-|--------|------|
-| **Task Granularity** | 1 PR = Exactly 1 `task()` call |
-| **Execution Mode** | `run_in_background=true` (Each PR runs independently) |
-| **Result Handling** | `background_output()` to collect results as they complete |
-| **Reporting** | IMMEDIATE streaming when each task finishes |
-
-### WHY 1 PR = 1 BACKGROUND TASK MATTERS
-
-- **ISOLATION**: Each PR analysis is independent - failures don't cascade
-- **PARALLELISM**: Multiple PRs analyzed concurrently for speed
-- **GRANULARITY**: Fine-grained control and monitoring per PR
-- **RESILIENCE**: If one PR analysis fails, others continue
-- **STREAMING**: Results flow in as soon as each task completes
-
----
-
-# CRITICAL: STREAMING ARCHITECTURE
-
-**PROCESS PRs WITH REAL-TIME STREAMING - NOT BATCHED**
-
-| WRONG | CORRECT |
-|----------|------------|
-| Fetch all → Wait for all agents → Report all at once | Fetch all → Launch 1 task per PR (background) → Stream results as each completes → Next |
-| "Processing 50 PRs... (wait 5 min) ...here are all results" | "PR #123 analysis complete... [RESULT] PR #124 analysis complete... [RESULT] ..." |
-| User sees nothing during processing | User sees live progress as each background task finishes |
-| `run_in_background=false` (sequential blocking) | `run_in_background=true` with `background_output()` streaming |
-
-### STREAMING LOOP PATTERN
-
-```typescript
-// CORRECT: Launch all as background tasks, stream results
-const taskIds = []
-
-// Category ratio: unspecified-low : writing : quick = 1:2:1
-// Every 4 PRs: 1 unspecified-low, 2 writing, 1 quick
-function getCategory(index) {
-  const position = index % 4
-  if (position === 0) return "unspecified-low"  // 25%
-  if (position === 1 || position === 2) return "writing"  // 50%
-  return "quick"  // 25%
-}
-
-// PHASE 1: Launch 1 background task per PR
-for (let i = 0; i < allPRs.length; i++) {
-  const pr = allPRs[i]
-  const category = getCategory(i)
-  
-  const taskId = await task(
-    category=category,
-    load_skills=[],
-    run_in_background=true,  // ← CRITICAL: Each PR is independent background task
-    prompt=`Analyze PR #${pr.number}...`
-  )
-  taskIds.push({ pr: pr.number, taskId, category })
-  console.log(`🚀 Launched background task for PR #${pr.number} (${category})`)
-}
-
-// PHASE 2: Stream results as they complete
-console.log(`\n📊 Streaming results for ${taskIds.length} PRs...`)
-
-const completed = new Set()
-while (completed.size < taskIds.length) {
-  for (const { pr, taskId } of taskIds) {
-    if (completed.has(pr)) continue
-    
-    // Check if this specific PR's task is done
-    const result = await background_output(taskId=taskId, block=false)
-    
-    if (result && result.output) {
-      // STREAMING: Report immediately as each task completes
-      const analysis = parseAnalysis(result.output)
-      reportRealtime(analysis)
-      completed.add(pr)
-      
-      console.log(`\n✅ PR #${pr} analysis complete (${completed.size}/${taskIds.length})`)
-    }
-  }
-  
-  // Small delay to prevent hammering
-  if (completed.size < taskIds.length) {
-    await new Promise(r => setTimeout(r, 1000))
-  }
-}
-```
-
-### WHY STREAMING MATTERS
-
-- **User sees progress immediately** - no 5-minute silence
-- **Early decisions visible** - maintainer can act on urgent PRs while others process
-- **Transparent** - user knows what's happening in real-time
-- **Fail-fast** - if something breaks, we already have partial results
-
----
-
-# CRITICAL: INITIALIZATION - TODO REGISTRATION (MANDATORY FIRST STEP)
-
-**BEFORE DOING ANYTHING ELSE, CREATE TODOS.**
-
-```typescript
-// Create todos immediately
-todowrite([
-  { id: "1", content: "Fetch all open PRs with exhaustive pagination", status: "in_progress", priority: "high" },
-  { id: "2", content: "Launch 1 background task per PR (1 PR = 1 task)", status: "pending", priority: "high" },
-  { id: "3", content: "Stream-process results as each task completes", status: "pending", priority: "high" },
-  { id: "4", content: "Execute conservative auto-close for eligible PRs", status: "pending", priority: "high" },
-  { id: "5", content: "Generate final comprehensive report", status: "pending", priority: "high" }
-])
-```
-
----
-
-# PHASE 1: PR Collection (EXHAUSTIVE Pagination)
-
-### 1.1 Use Bundled Script (MANDATORY)
-
-```bash
-./scripts/gh_fetch.py prs --output json
-```
-
-### 1.2 Fallback: Manual Pagination
-
-```bash
-REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
-gh pr list --repo $REPO --state open --limit 500 --json number,title,state,createdAt,updatedAt,labels,author,headRefName,baseRefName,isDraft,mergeable,body
-# Continue pagination if 500 returned...
-```
-
-**AFTER Phase 1:** Update todo status to completed, mark Phase 2 as in_progress.
-
----
-
-# PHASE 2: LAUNCH 1 BACKGROUND TASK PER PR
-
-## THE 1-PR-1-TASK PATTERN (MANDATORY)
-
-**CRITICAL: DO NOT BATCH MULTIPLE PRs INTO ONE TASK**
-
-```typescript
-// Collection for tracking
-const taskMap = new Map()  // prNumber -> taskId
-
-// Category ratio: unspecified-low : writing : quick = 1:2:1
-// Every 4 PRs: 1 unspecified-low, 2 writing, 1 quick
-function getCategory(index) {
-  const position = index % 4
-  if (position === 0) return "unspecified-low"  // 25%
-  if (position === 1 || position === 2) return "writing"  // 50%
-  return "quick"  // 25%
-}
-
-// Launch 1 background task per PR
-for (let i = 0; i < allPRs.length; i++) {
-  const pr = allPRs[i]
-  const category = getCategory(i)
-  
-  console.log(`🚀 Launching background task for PR #${pr.number} (${category})...`)
-  
-  const taskId = await task(
-    category=category,
-    load_skills=[],
-    run_in_background=true,  // ← BACKGROUND TASK: Each PR runs independently
-    prompt=`
-## TASK
-Analyze GitHub PR #${pr.number} for ${REPO}.
-
-## PR DATA
-- Number: #${pr.number}
-- Title: ${pr.title}
-- State: ${pr.state}
-- Author: ${pr.author.login}
-- Created: ${pr.createdAt}
-- Updated: ${pr.updatedAt}
-- Labels: ${pr.labels.map(l => l.name).join(', ')}
-- Head Branch: ${pr.headRefName}
-- Base Branch: ${pr.baseRefName}
-- Is Draft: ${pr.isDraft}
-- Mergeable: ${pr.mergeable}
-
-## PR BODY
-${pr.body}
-
-## FETCH ADDITIONAL CONTEXT
-1. Fetch PR comments: gh pr view ${pr.number} --repo ${REPO} --json comments
-2. Fetch PR reviews: gh pr view ${pr.number} --repo ${REPO} --json reviews
-3. Fetch PR files changed: gh pr view ${pr.number} --repo ${REPO} --json files
-4. Check if branch exists: git ls-remote --heads origin ${pr.headRefName}
-5. Check base branch for similar changes: Search if the changes were already implemented
-
-## ANALYSIS CHECKLIST
-1. **MERGE_READY**: Can this PR be merged? (approvals, CI passed, no conflicts, not draft)
-2. **PROJECT_ALIGNED**: Does this PR align with current project direction?
-3. **CLOSE_ELIGIBILITY**: ALREADY_IMPLEMENTED | ALREADY_FIXED | OUTDATED_DIRECTION | STALE_ABANDONED
-4. **STALENESS**: ACTIVE (<30d) | STALE (30-180d) | ABANDONED (180d+)
-
-## CONSERVATIVE CLOSE CRITERIA
-MAY CLOSE ONLY IF:
-- Exact same change already exists in main
-- A merged PR already solved this differently
-- Project explicitly deprecated the feature
-- Author unresponsive for 6+ months despite requests
-
-## RETURN FORMAT (STRICT)
-\`\`\`
-PR: #${pr.number}
-TITLE: ${pr.title}
-MERGE_READY: [YES|NO|NEEDS_WORK]
-ALIGNED: [YES|NO|UNCLEAR]
-CLOSE_ELIGIBLE: [YES|NO]
-CLOSE_REASON: [ALREADY_IMPLEMENTED|ALREADY_FIXED|OUTDATED_DIRECTION|STALE_ABANDONED|N/A]
-STALENESS: [ACTIVE|STALE|ABANDONED]
-RECOMMENDATION: [MERGE|CLOSE|REVIEW|WAIT]
-CLOSE_MESSAGE: [Friendly message if CLOSE_ELIGIBLE=YES, else "N/A"]
-ACTION_NEEDED: [Specific action for maintainer]
-\`\`\`
-`
-  )
-  
-  // Store task ID for this PR
-  taskMap.set(pr.number, taskId)
-}
-
-console.log(`\n✅ Launched ${taskMap.size} background tasks (1 per PR)`)
-```
-
-**AFTER Phase 2:** Update todo, mark Phase 3 as in_progress.
-
----
-
-# PHASE 3: STREAM RESULTS AS EACH TASK COMPLETES
-
-## REAL-TIME STREAMING COLLECTION
-
-```typescript
-const results = []
-const autoCloseable = []
-const readyToMerge = []
-const needsReview = []
-const needsWork = []
-const stale = []
-const drafts = []
-
-const completedPRs = new Set()
-const totalPRs = taskMap.size
-
-console.log(`\n📊 Streaming results for ${totalPRs} PRs...`)
-
-// Stream results as each background task completes
-while (completedPRs.size < totalPRs) {
-  let newCompletions = 0
-  
-  for (const [prNumber, taskId] of taskMap) {
-    if (completedPRs.has(prNumber)) continue
-    
-    // Non-blocking check for this specific task
-    const output = await background_output(task_id=taskId, block=false)
-    
-    if (output && output.length > 0) {
-      // Parse the completed analysis
-      const analysis = parseAnalysis(output)
-      results.push(analysis)
-      completedPRs.add(prNumber)
-      newCompletions++
-      
-      // REAL-TIME STREAMING REPORT
-      console.log(`\n🔄 PR #${prNumber}: ${analysis.TITLE.substring(0, 60)}...`)
-      
-      // Immediate categorization & reporting
-      if (analysis.CLOSE_ELIGIBLE === 'YES') {
-        autoCloseable.push(analysis)
-        console.log(`   ⚠️  AUTO-CLOSE CANDIDATE: ${analysis.CLOSE_REASON}`)
-      } else if (analysis.MERGE_READY === 'YES') {
-        readyToMerge.push(analysis)
-        console.log(`   ✅ READY TO MERGE`)
-      } else if (analysis.RECOMMENDATION === 'REVIEW') {
-        needsReview.push(analysis)
-        console.log(`   👀 NEEDS REVIEW`)
-      } else if (analysis.RECOMMENDATION === 'WAIT') {
-        needsWork.push(analysis)
-        console.log(`   ⏳ WAITING FOR AUTHOR`)
-      } else if (analysis.STALENESS === 'STALE' || analysis.STALENESS === 'ABANDONED') {
-        stale.push(analysis)
-        console.log(`   💤 ${analysis.STALENESS}`)
-      } else {
-        drafts.push(analysis)
-        console.log(`   📝 DRAFT`)
-      }
-      
-      console.log(`   📊 Action: ${analysis.ACTION_NEEDED}`)
-      
-      // Progress update every 5 completions
-      if (completedPRs.size % 5 === 0) {
-        console.log(`\n📈 PROGRESS: ${completedPRs.size}/${totalPRs} PRs analyzed`)
-        console.log(`   Ready: ${readyToMerge.length} | Review: ${needsReview.length} | Wait: ${needsWork.length} | Stale: ${stale.length} | Draft: ${drafts.length} | Close-Candidate: ${autoCloseable.length}`)
-      }
-    }
-  }
-  
-  // If no new completions, wait briefly before checking again
-  if (newCompletions === 0 && completedPRs.size < totalPRs) {
-    await new Promise(r => setTimeout(r, 2000))
-  }
-}
-
-console.log(`\n✅ All ${totalPRs} PRs analyzed`)
-```
-
----
-
-# PHASE 4: Auto-Close Execution (CONSERVATIVE)
-
-### 4.1 Confirm and Close
-
-**Ask for confirmation before closing (unless user explicitly said auto-close is OK)**
-
-```typescript
-if (autoCloseable.length > 0) {
-  console.log(`\n🚨 FOUND ${autoCloseable.length} PR(s) ELIGIBLE FOR AUTO-CLOSE:`)
-  
-  for (const pr of autoCloseable) {
-    console.log(`   #${pr.PR}: ${pr.TITLE} (${pr.CLOSE_REASON})`)
-  }
-  
-  // Close them one by one with progress
-  for (const pr of autoCloseable) {
-    console.log(`\n   Closing #${pr.PR}...`)
-    
-    await bash({
-      command: `gh pr close ${pr.PR} --repo ${REPO} --comment "${pr.CLOSE_MESSAGE}"`,
-      description: `Close PR #${pr.PR} with friendly message`
-    })
-    
-    console.log(`   ✅ Closed #${pr.PR}`)
-  }
-}
-```
-
----
-
-# PHASE 5: FINAL COMPREHENSIVE REPORT
-
-**GENERATE THIS AT THE VERY END - AFTER ALL PROCESSING**
-
-```markdown
-# PR Triage Report - ${REPO}
-
-**Generated:** ${new Date().toISOString()}
-**Total PRs Analyzed:** ${results.length}
-**Processing Mode:** STREAMING (1 PR = 1 background task, real-time results)
-
----
-
-## 📊 Summary
-
-| Category | Count | Status |
-|----------|-------|--------|
-| ✅ Ready to Merge | ${readyToMerge.length} | Action: Merge immediately |
-| ⚠️ Auto-Closed | ${autoCloseable.length} | Already processed |
-| 👀 Needs Review | ${needsReview.length} | Action: Assign reviewers |
-| ⏳ Needs Work | ${needsWork.length} | Action: Comment guidance |
-| 💤 Stale | ${stale.length} | Action: Follow up |
-| 📝 Draft | ${drafts.length} | No action needed |
-
----
-
-## ✅ Ready to Merge
-
-${readyToMerge.map(pr => `| #${pr.PR} | ${pr.TITLE.substring(0, 50)}... |`).join('\n')}
-
-**Action:** These PRs can be merged immediately.
-
----
-
-## ⚠️ Auto-Closed (During This Triage)
-
-${autoCloseable.map(pr => `| #${pr.PR} | ${pr.TITLE.substring(0, 40)}... | ${pr.CLOSE_REASON} |`).join('\n')}
-
----
-
-## 👀 Needs Review
-
-${needsReview.map(pr => `| #${pr.PR} | ${pr.TITLE.substring(0, 50)}... |`).join('\n')}
-
-**Action:** Assign maintainers for review.
-
----
-
-## ⏳ Needs Work
-
-${needsWork.map(pr => `| #${pr.PR} | ${pr.TITLE.substring(0, 50)}... | ${pr.ACTION_NEEDED} |`).join('\n')}
-
----
-
-## 💤 Stale PRs
-
-${stale.map(pr => `| #${pr.PR} | ${pr.TITLE.substring(0, 40)}... | ${pr.STALENESS} |`).join('\n')}
-
----
-
-## 📝 Draft PRs
-
-${drafts.map(pr => `| #${pr.PR} | ${pr.TITLE.substring(0, 50)}... |`).join('\n')}
-
----
-
-## 🎯 Immediate Actions
-
-1. **Merge:** ${readyToMerge.length} PRs ready for immediate merge
-2. **Review:** ${needsReview.length} PRs awaiting maintainer attention
-3. **Follow Up:** ${stale.length} stale PRs need author ping
-
----
-
-## Processing Log
-
-${results.map((r, i) => `${i+1}. #${r.PR}: ${r.RECOMMENDATION} (${r.MERGE_READY === 'YES' ? 'ready' : r.CLOSE_ELIGIBLE === 'YES' ? 'close' : 'needs attention'})`).join('\n')}
-```
-
----
-
-## CRITICAL ANTI-PATTERNS (BLOCKING VIOLATIONS)
-
-| Violation | Why It's Wrong | Severity |
-|-----------|----------------|----------|
-| **Batch multiple PRs in one task** | Violates 1 PR = 1 task rule | CRITICAL |
-| **Use `run_in_background=false`** | No parallelism, slower execution | CRITICAL |
-| **Collect all tasks, report at end** | Loses streaming benefit | CRITICAL |
-| **No `background_output()` polling** | Can't stream results | CRITICAL |
-| No progress updates | User doesn't know if stuck or working | HIGH |
-
----
-
-## EXECUTION CHECKLIST
-
-- [ ] Created todos before starting
-- [ ] Fetched ALL PRs with exhaustive pagination
-- [ ] **LAUNCHED**: 1 background task per PR (`run_in_background=true`)
-- [ ] **STREAMED**: Results via `background_output()` as each task completes
-- [ ] Showed live progress every 5 PRs
-- [ ] Real-time categorization visible to user
-- [ ] Conservative auto-close with confirmation
-- [ ] **FINAL**: Comprehensive summary report at end
-- [ ] All todos marked complete
-
----
-
-## Quick Start
-
-When invoked, immediately:
-
-1. **CREATE TODOS**
-2. `gh repo view --json nameWithOwner -q .nameWithOwner`
-3. Exhaustive pagination for ALL open PRs
-4. **LAUNCH**: For each PR:
-   - `task(run_in_background=true)` - 1 task per PR
-   - Store taskId mapped to PR number
-5. **STREAM**: Poll `background_output()` for each task:
-   - As each completes, immediately report result
-   - Categorize in real-time
-   - Show progress every 5 completions
-6. Auto-close eligible PRs
-7. **GENERATE FINAL COMPREHENSIVE REPORT**

.opencode/skills/github-pr-triage/scripts/gh_fetch.py

@@ -1,373 +0,0 @@
-#!/usr/bin/env -S uv run --script
-# /// script
-# requires-python = ">=3.11"
-# dependencies = [
-#     "typer>=0.12.0",
-#     "rich>=13.0.0",
-# ]
-# ///
-"""
-GitHub Issues/PRs Fetcher with Exhaustive Pagination.
-
-Fetches ALL issues and/or PRs from a GitHub repository using gh CLI.
-Implements proper pagination to ensure no items are missed.
-
-Usage:
-    ./gh_fetch.py issues                    # Fetch all issues
-    ./gh_fetch.py prs                       # Fetch all PRs
-    ./gh_fetch.py all                       # Fetch both issues and PRs
-    ./gh_fetch.py issues --hours 48         # Issues from last 48 hours
-    ./gh_fetch.py prs --state open          # Only open PRs
-    ./gh_fetch.py all --repo owner/repo     # Specify repository
-"""
-
-import asyncio
-import json
-from datetime import UTC, datetime, timedelta
-from enum import Enum
-from typing import Annotated
-
-import typer
-from rich.console import Console
-from rich.panel import Panel
-from rich.progress import Progress, TaskID
-from rich.table import Table
-
-app = typer.Typer(
-    name="gh_fetch",
-    help="Fetch GitHub issues/PRs with exhaustive pagination.",
-    no_args_is_help=True,
-)
-console = Console()
-
-BATCH_SIZE = 500  # Maximum allowed by GitHub API
-
-
-class ItemState(str, Enum):
-    ALL = "all"
-    OPEN = "open"
-    CLOSED = "closed"
-
-
-class OutputFormat(str, Enum):
-    JSON = "json"
-    TABLE = "table"
-    COUNT = "count"
-
-
-async def run_gh_command(args: list[str]) -> tuple[str, str, int]:
-    """Run gh CLI command asynchronously."""
-    proc = await asyncio.create_subprocess_exec(
-        "gh",
-        *args,
-        stdout=asyncio.subprocess.PIPE,
-        stderr=asyncio.subprocess.PIPE,
-    )
-    stdout, stderr = await proc.communicate()
-    return stdout.decode(), stderr.decode(), proc.returncode or 0
-
-
-async def get_current_repo() -> str:
-    """Get the current repository from gh CLI."""
-    stdout, stderr, code = await run_gh_command(["repo", "view", "--json", "nameWithOwner", "-q", ".nameWithOwner"])
-    if code != 0:
-        console.print(f"[red]Error getting current repo: {stderr}[/red]")
-        raise typer.Exit(1)
-    return stdout.strip()
-
-
-async def fetch_items_page(
-    repo: str,
-    item_type: str,  # "issue" or "pr"
-    state: str,
-    limit: int,
-    search_filter: str = "",
-) -> list[dict]:
-    """Fetch a single page of issues or PRs."""
-    cmd = [
-        item_type,
-        "list",
-        "--repo",
-        repo,
-        "--state",
-        state,
-        "--limit",
-        str(limit),
-        "--json",
-        "number,title,state,createdAt,updatedAt,labels,author,body",
-    ]
-    if search_filter:
-        cmd.extend(["--search", search_filter])
-
-    stdout, stderr, code = await run_gh_command(cmd)
-    if code != 0:
-        console.print(f"[red]Error fetching {item_type}s: {stderr}[/red]")
-        return []
-
-    try:
-        return json.loads(stdout) if stdout.strip() else []
-    except json.JSONDecodeError:
-        console.print(f"[red]Error parsing {item_type} response[/red]")
-        return []
-
-
-async def fetch_all_items(
-    repo: str,
-    item_type: str,
-    state: str,
-    hours: int | None,
-    progress: Progress,
-    task_id: TaskID,
-) -> list[dict]:
-    """Fetch ALL items with exhaustive pagination."""
-    all_items: list[dict] = []
-    page = 1
-
-    # First fetch
-    progress.update(task_id, description=f"[cyan]Fetching {item_type}s page {page}...")
-    items = await fetch_items_page(repo, item_type, state, BATCH_SIZE)
-    fetched_count = len(items)
-    all_items.extend(items)
-
-    console.print(f"[dim]Page {page}: fetched {fetched_count} {item_type}s[/dim]")
-
-    # Continue pagination if we got exactly BATCH_SIZE (more pages exist)
-    while fetched_count == BATCH_SIZE:
-        page += 1
-        progress.update(task_id, description=f"[cyan]Fetching {item_type}s page {page}...")
-
-        # Use created date of last item to paginate
-        last_created = all_items[-1].get("createdAt", "")
-        if not last_created:
-            break
-
-        search_filter = f"created:<{last_created}"
-        items = await fetch_items_page(repo, item_type, state, BATCH_SIZE, search_filter)
-        fetched_count = len(items)
-
-        if fetched_count == 0:
-            break
-
-        # Deduplicate by number
-        existing_numbers = {item["number"] for item in all_items}
-        new_items = [item for item in items if item["number"] not in existing_numbers]
-        all_items.extend(new_items)
-
-        console.print(
-            f"[dim]Page {page}: fetched {fetched_count}, added {len(new_items)} new (total: {len(all_items)})[/dim]"
-        )
-
-        # Safety limit
-        if page > 20:
-            console.print("[yellow]Safety limit reached (20 pages)[/yellow]")
-            break
-
-    # Filter by time if specified
-    if hours is not None:
-        cutoff = datetime.now(UTC) - timedelta(hours=hours)
-        cutoff_str = cutoff.isoformat()
-
-        original_count = len(all_items)
-        all_items = [
-            item
-            for item in all_items
-            if item.get("createdAt", "") >= cutoff_str or item.get("updatedAt", "") >= cutoff_str
-        ]
-        filtered_count = original_count - len(all_items)
-        if filtered_count > 0:
-            console.print(f"[dim]Filtered out {filtered_count} items older than {hours} hours[/dim]")
-
-    return all_items
-
-
-def display_table(items: list[dict], item_type: str) -> None:
-    """Display items in a Rich table."""
-    table = Table(title=f"{item_type.upper()}s ({len(items)} total)")
-    table.add_column("#", style="cyan", width=6)
-    table.add_column("Title", style="white", max_width=50)
-    table.add_column("State", style="green", width=8)
-    table.add_column("Author", style="yellow", width=15)
-    table.add_column("Labels", style="magenta", max_width=30)
-    table.add_column("Updated", style="dim", width=12)
-
-    for item in items[:50]:  # Show first 50
-        labels = ", ".join(label.get("name", "") for label in item.get("labels", []))
-        updated = item.get("updatedAt", "")[:10]
-        author = item.get("author", {}).get("login", "unknown")
-
-        table.add_row(
-            str(item.get("number", "")),
-            (item.get("title", "")[:47] + "...") if len(item.get("title", "")) > 50 else item.get("title", ""),
-            item.get("state", ""),
-            author,
-            (labels[:27] + "...") if len(labels) > 30 else labels,
-            updated,
-        )
-
-    console.print(table)
-    if len(items) > 50:
-        console.print(f"[dim]... and {len(items) - 50} more items[/dim]")
-
-
-@app.command()
-def issues(
-    repo: Annotated[str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")] = None,
-    state: Annotated[ItemState, typer.Option("--state", "-s", help="Issue state filter")] = ItemState.ALL,
-    hours: Annotated[
-        int | None,
-        typer.Option("--hours", "-h", help="Only issues from last N hours (created or updated)"),
-    ] = None,
-    output: Annotated[OutputFormat, typer.Option("--output", "-o", help="Output format")] = OutputFormat.TABLE,
-) -> None:
-    """Fetch all issues with exhaustive pagination."""
-
-    async def async_main() -> None:
-        target_repo = repo or await get_current_repo()
-
-        console.print(f"""
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
-[cyan]Repository:[/cyan] {target_repo}
-[cyan]State:[/cyan] {state.value}
-[cyan]Time filter:[/cyan] {f"Last {hours} hours" if hours else "All time"}
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
-""")
-
-        with Progress(console=console) as progress:
-            task: TaskID = progress.add_task("[cyan]Fetching issues...", total=None)
-
-            items = await fetch_all_items(target_repo, "issue", state.value, hours, progress, task)
-
-            progress.update(task, description="[green]Complete!", completed=100, total=100)
-
-        console.print(
-            Panel(
-                f"[green]✓ Found {len(items)} issues[/green]",
-                title="[green]Pagination Complete[/green]",
-                border_style="green",
-            )
-        )
-
-        if output == OutputFormat.JSON:
-            console.print(json.dumps(items, indent=2, ensure_ascii=False))
-        elif output == OutputFormat.TABLE:
-            display_table(items, "issue")
-        else:  # COUNT
-            console.print(f"Total issues: {len(items)}")
-
-    asyncio.run(async_main())
-
-
-@app.command()
-def prs(
-    repo: Annotated[str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")] = None,
-    state: Annotated[ItemState, typer.Option("--state", "-s", help="PR state filter")] = ItemState.OPEN,
-    hours: Annotated[
-        int | None,
-        typer.Option("--hours", "-h", help="Only PRs from last N hours (created or updated)"),
-    ] = None,
-    output: Annotated[OutputFormat, typer.Option("--output", "-o", help="Output format")] = OutputFormat.TABLE,
-) -> None:
-    """Fetch all PRs with exhaustive pagination."""
-
-    async def async_main() -> None:
-        target_repo = repo or await get_current_repo()
-
-        console.print(f"""
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
-[cyan]Repository:[/cyan] {target_repo}
-[cyan]State:[/cyan] {state.value}
-[cyan]Time filter:[/cyan] {f"Last {hours} hours" if hours else "All time"}
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
-""")
-
-        with Progress(console=console) as progress:
-            task: TaskID = progress.add_task("[cyan]Fetching PRs...", total=None)
-
-            items = await fetch_all_items(target_repo, "pr", state.value, hours, progress, task)
-
-            progress.update(task, description="[green]Complete!", completed=100, total=100)
-
-        console.print(
-            Panel(
-                f"[green]✓ Found {len(items)} PRs[/green]",
-                title="[green]Pagination Complete[/green]",
-                border_style="green",
-            )
-        )
-
-        if output == OutputFormat.JSON:
-            console.print(json.dumps(items, indent=2, ensure_ascii=False))
-        elif output == OutputFormat.TABLE:
-            display_table(items, "pr")
-        else:  # COUNT
-            console.print(f"Total PRs: {len(items)}")
-
-    asyncio.run(async_main())
-
-
-@app.command(name="all")
-def fetch_all(
-    repo: Annotated[str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")] = None,
-    state: Annotated[ItemState, typer.Option("--state", "-s", help="State filter")] = ItemState.ALL,
-    hours: Annotated[
-        int | None,
-        typer.Option("--hours", "-h", help="Only items from last N hours (created or updated)"),
-    ] = None,
-    output: Annotated[OutputFormat, typer.Option("--output", "-o", help="Output format")] = OutputFormat.TABLE,
-) -> None:
-    """Fetch all issues AND PRs with exhaustive pagination."""
-
-    async def async_main() -> None:
-        target_repo = repo or await get_current_repo()
-
-        console.print(f"""
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
-[cyan]Repository:[/cyan] {target_repo}
-[cyan]State:[/cyan] {state.value}
-[cyan]Time filter:[/cyan] {f"Last {hours} hours" if hours else "All time"}
-[cyan]Fetching:[/cyan] Issues AND PRs
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
-""")
-
-        with Progress(console=console) as progress:
-            issues_task: TaskID = progress.add_task("[cyan]Fetching issues...", total=None)
-            prs_task: TaskID = progress.add_task("[cyan]Fetching PRs...", total=None)
-
-            # Fetch in parallel
-            issues_items, prs_items = await asyncio.gather(
-                fetch_all_items(target_repo, "issue", state.value, hours, progress, issues_task),
-                fetch_all_items(target_repo, "pr", state.value, hours, progress, prs_task),
-            )
-
-            progress.update(
-                issues_task,
-                description="[green]Issues complete!",
-                completed=100,
-                total=100,
-            )
-            progress.update(prs_task, description="[green]PRs complete!", completed=100, total=100)
-
-        console.print(
-            Panel(
-                f"[green]✓ Found {len(issues_items)} issues and {len(prs_items)} PRs[/green]",
-                title="[green]Pagination Complete[/green]",
-                border_style="green",
-            )
-        )
-
-        if output == OutputFormat.JSON:
-            result = {"issues": issues_items, "prs": prs_items}
-            console.print(json.dumps(result, indent=2, ensure_ascii=False))
-        elif output == OutputFormat.TABLE:
-            display_table(issues_items, "issue")
-            console.print("")
-            display_table(prs_items, "pr")
-        else:  # COUNT
-            console.print(f"Total issues: {len(issues_items)}")
-            console.print(f"Total PRs: {len(prs_items)}")
-
-    asyncio.run(async_main())
-
-
-if __name__ == "__main__":
-    app()

.opencode/skills/github-triage/SKILL.md

@@ -0,0 +1,482 @@
+---
+name: github-triage
+description: "Unified GitHub triage for issues AND PRs. 1 item = 1 background task (category: free). Issues: answer questions from codebase, analyze bugs. PRs: review bugfixes, merge safe ones. All parallel, all background. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'."
+---
+
+# GitHub Triage — Unified Issue & PR Processor
+
+<role>
+You are a GitHub triage orchestrator. You fetch all open issues and PRs, classify each one, then spawn exactly 1 background subagent per item using `category="free"`. Each subagent analyzes its item, takes action (comment/close/merge/report), and records results via TaskCreate.
+</role>
+
+---
+
+## ARCHITECTURE
+
+```
+1 issue or PR = 1 TaskCreate = 1 task(category="free", run_in_background=true)
+```
+
+| Rule | Value |
+|------|-------|
+| Category for ALL subagents | `free` |
+| Execution mode | `run_in_background=true` |
+| Parallelism | ALL items launched simultaneously |
+| Result tracking | Each subagent calls `TaskCreate` with its findings |
+| Result collection | `background_output()` polling loop |
+
+---
+
+## PHASE 1: FETCH ALL OPEN ITEMS
+
+<fetch>
+Run these commands to collect data. Use the bundled script if available, otherwise fall back to gh CLI.
+
+```bash
+REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
+
+# Issues: all open
+gh issue list --repo $REPO --state open --limit 500 \
+  --json number,title,state,createdAt,updatedAt,labels,author,body,comments
+
+# PRs: all open
+gh pr list --repo $REPO --state open --limit 500 \
+  --json number,title,state,createdAt,updatedAt,labels,author,body,headRefName,baseRefName,isDraft,mergeable,reviewDecision,statusCheckRollup
+```
+
+If either returns exactly 500 results, paginate using `--search "created:<LAST_CREATED_AT"` until exhausted.
+</fetch>
+
+---
+
+## PHASE 2: CLASSIFY EACH ITEM
+
+For each item, determine its type based on title, labels, and body content:
+
+<classification>
+
+### Issues
+
+| Type | Detection | Action Path |
+|------|-----------|-------------|
+| `ISSUE_QUESTION` | Title contains `[Question]`, `[Discussion]`, `?`, or body is asking "how to" / "why does" / "is it possible" | SUBAGENT_ISSUE_QUESTION |
+| `ISSUE_BUG` | Title contains `[Bug]`, `Bug:`, body describes unexpected behavior, error messages, stack traces | SUBAGENT_ISSUE_BUG |
+| `ISSUE_FEATURE` | Title contains `[Feature]`, `[RFE]`, `[Enhancement]`, `Feature Request`, `Proposal` | SUBAGENT_ISSUE_FEATURE |
+| `ISSUE_OTHER` | Anything else | SUBAGENT_ISSUE_OTHER |
+
+### PRs
+
+| Type | Detection | Action Path |
+|------|-----------|-------------|
+| `PR_BUGFIX` | Title starts with `fix`, `fix:`, `fix(`, branch contains `fix/`, `bugfix/`, or labels include `bug` | SUBAGENT_PR_BUGFIX |
+| `PR_OTHER` | Everything else (feat, refactor, docs, chore, etc.) | SUBAGENT_PR_OTHER |
+
+</classification>
+
+---
+
+## PHASE 3: SPAWN 1 BACKGROUND TASK PER ITEM
+
+For EVERY item, create a TaskCreate entry first, then spawn a background task.
+
+```
+For each item:
+  1. TaskCreate(subject="Triage: #{number} {title}")
+  2. task(category="free", run_in_background=true, load_skills=[], prompt=SUBAGENT_PROMPT)
+  3. Store mapping: item_number -> { task_id, background_task_id }
+```
+
+---
+
+## SUBAGENT PROMPT TEMPLATES
+
+Each subagent gets an explicit, step-by-step prompt. Free models are limited — leave NOTHING implicit.
+
+---
+
+### SUBAGENT_ISSUE_QUESTION
+
+<issue_question_prompt>
+
+```
+You are a GitHub issue responder for the repository {REPO}.
+
+ITEM:
+- Issue #{number}: {title}
+- Author: {author}
+- Body: {body}
+- Comments: {comments_summary}
+
+YOUR JOB:
+1. Read the issue carefully. Understand what the user is asking.
+2. Search the codebase to find the answer. Use Grep and Read tools.
+   - Search for relevant file names, function names, config keys mentioned in the issue.
+   - Read the files you find to understand how the feature works.
+3. Decide: Can you answer this clearly and accurately from the codebase?
+
+IF YES (you found a clear, accurate answer):
+  Step A: Write a helpful comment. The comment MUST:
+    - Start with exactly: [sisyphus-bot]
+    - Be warm, friendly, and thorough
+    - Include specific file paths and code references
+    - Include code snippets or config examples if helpful
+    - End with "Feel free to reopen if this doesn't resolve your question!"
+  Step B: Post the comment:
+    gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"
+  Step C: Close the issue:
+    gh issue close {number} --repo {REPO}
+  Step D: Report back with this EXACT format:
+    ACTION: ANSWERED_AND_CLOSED
+    COMMENT_POSTED: yes
+    SUMMARY: [1-2 sentence summary of your answer]
+
+IF NO (not enough info in codebase, or answer is uncertain):
+  Report back with:
+    ACTION: NEEDS_MANUAL_ATTENTION
+    REASON: [why you couldn't answer — be specific]
+    PARTIAL_FINDINGS: [what you DID find, if anything]
+
+RULES:
+- NEVER guess. Only answer if the codebase clearly supports your answer.
+- NEVER make up file paths or function names.
+- The [sisyphus-bot] prefix is MANDATORY on every comment you post.
+- Be genuinely helpful — imagine you're a senior maintainer who cares about the community.
+```
+
+</issue_question_prompt>
+
+---
+
+### SUBAGENT_ISSUE_BUG
+
+<issue_bug_prompt>
+
+```
+You are a GitHub bug analyzer for the repository {REPO}.
+
+ITEM:
+- Issue #{number}: {title}
+- Author: {author}
+- Body: {body}
+- Comments: {comments_summary}
+
+YOUR JOB:
+1. Read the issue carefully. Understand the reported bug:
+   - What behavior does the user expect?
+   - What behavior do they actually see?
+   - What steps reproduce it?
+2. Search the codebase for the relevant code. Use Grep and Read tools.
+   - Find the files/functions mentioned or related to the bug.
+   - Read them carefully and trace the logic.
+3. Determine one of three outcomes:
+
+OUTCOME A — CONFIRMED BUG (you found the problematic code):
+  Step 1: Post a comment on the issue. The comment MUST:
+    - Start with exactly: [sisyphus-bot]
+    - Apologize sincerely for the inconvenience ("We're sorry you ran into this issue.")
+    - Briefly acknowledge what the bug is
+    - Say "We've identified the root cause and will work on a fix."
+    - Do NOT reveal internal implementation details unnecessarily
+  Step 2: Post the comment:
+    gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"
+  Step 3: Report back with:
+    ACTION: CONFIRMED_BUG
+    ROOT_CAUSE: [which file, which function, what goes wrong]
+    FIX_APPROACH: [how to fix it — be specific: "In {file}, line ~{N}, change X to Y because Z"]
+    SEVERITY: [LOW|MEDIUM|HIGH|CRITICAL]
+    AFFECTED_FILES: [list of files that need changes]
+
+OUTCOME B — NOT A BUG (user misunderstanding, provably correct behavior):
+  ONLY choose this if you can RIGOROUSLY PROVE the behavior is correct.
+  Step 1: Post a comment. The comment MUST:
+    - Start with exactly: [sisyphus-bot]
+    - Be kind and empathetic — never condescending
+    - Explain clearly WHY the current behavior is correct
+    - Include specific code references or documentation links
+    - Offer a workaround or alternative if possible
+    - End with "Please let us know if you have further questions!"
+  Step 2: Post the comment:
+    gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"
+  Step 3: DO NOT close the issue. Let the user or maintainer decide.
+  Step 4: Report back with:
+    ACTION: NOT_A_BUG
+    EXPLANATION: [why this is correct behavior]
+    PROOF: [specific code reference proving it]
+
+OUTCOME C — UNCLEAR (can't determine from codebase alone):
+  Report back with:
+    ACTION: NEEDS_INVESTIGATION
+    FINDINGS: [what you found so far]
+    BLOCKERS: [what's preventing you from determining the cause]
+    SUGGESTED_NEXT_STEPS: [what a human should look at]
+
+RULES:
+- NEVER guess at root causes. Only report CONFIRMED_BUG if you found the exact problematic code.
+- NEVER close bug issues yourself. Only comment.
+- For OUTCOME B (not a bug): you MUST have rigorous proof. If there's ANY doubt, choose OUTCOME C instead.
+- The [sisyphus-bot] prefix is MANDATORY on every comment.
+- When apologizing, be genuine. The user took time to report this.
+```
+
+</issue_bug_prompt>
+
+---
+
+### SUBAGENT_ISSUE_FEATURE
+
+<issue_feature_prompt>
+
+```
+You are a GitHub feature request analyzer for the repository {REPO}.
+
+ITEM:
+- Issue #{number}: {title}
+- Author: {author}
+- Body: {body}
+- Comments: {comments_summary}
+
+YOUR JOB:
+1. Read the feature request.
+2. Search the codebase to check if this feature already exists (partially or fully).
+3. Assess feasibility and alignment with the project.
+
+Report back with:
+  ACTION: FEATURE_ASSESSED
+  ALREADY_EXISTS: [YES_FULLY | YES_PARTIALLY | NO]
+  IF_EXISTS: [where in the codebase, how to use it]
+  FEASIBILITY: [EASY | MODERATE | HARD | ARCHITECTURAL_CHANGE]
+  RELEVANT_FILES: [files that would need changes]
+  NOTES: [any observations about implementation approach]
+
+If the feature already fully exists:
+  Post a comment (prefix: [sisyphus-bot]) explaining how to use the existing feature with examples.
+  gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"
+
+RULES:
+- Do NOT close feature requests.
+- The [sisyphus-bot] prefix is MANDATORY on any comment.
+```
+
+</issue_feature_prompt>
+
+---
+
+### SUBAGENT_ISSUE_OTHER
+
+<issue_other_prompt>
+
+```
+You are a GitHub issue analyzer for the repository {REPO}.
+
+ITEM:
+- Issue #{number}: {title}
+- Author: {author}
+- Body: {body}
+- Comments: {comments_summary}
+
+YOUR JOB:
+Quickly assess this issue and report:
+  ACTION: ASSESSED
+  TYPE_GUESS: [QUESTION | BUG | FEATURE | DISCUSSION | META | STALE]
+  SUMMARY: [1-2 sentence summary]
+  NEEDS_ATTENTION: [YES | NO]
+  SUGGESTED_LABEL: [if any]
+
+Do NOT post comments. Do NOT close. Just analyze and report.
+```
+
+</issue_other_prompt>
+
+---
+
+### SUBAGENT_PR_BUGFIX
+
+<pr_bugfix_prompt>
+
+```
+You are a GitHub PR reviewer for the repository {REPO}.
+
+ITEM:
+- PR #{number}: {title}
+- Author: {author}
+- Base: {baseRefName}
+- Head: {headRefName}
+- Draft: {isDraft}
+- Mergeable: {mergeable}
+- Review Decision: {reviewDecision}
+- CI Status: {statusCheckRollup_summary}
+- Body: {body}
+
+YOUR JOB:
+1. Fetch PR details (DO NOT checkout the branch — read-only analysis):
+   gh pr view {number} --repo {REPO} --json files,reviews,comments,statusCheckRollup,reviewDecision
+2. Read the changed files list. For each changed file, use `gh api repos/{REPO}/pulls/{number}/files` to see the diff.
+3. Search the codebase to understand what the PR is fixing and whether the fix is correct.
+4. Evaluate merge safety:
+
+MERGE CONDITIONS (ALL must be true for auto-merge):
+  a. CI status checks: ALL passing (no failures, no pending)
+  b. Review decision: APPROVED
+  c. The fix is clearly correct — addresses an obvious, unambiguous bug
+  d. No risky side effects (no architectural changes, no breaking changes)
+  e. Not a draft PR
+  f. Mergeable state is clean (no conflicts)
+
+IF ALL MERGE CONDITIONS MET:
+  Step 1: Merge the PR:
+    gh pr merge {number} --repo {REPO} --squash --auto
+  Step 2: Report back with:
+    ACTION: MERGED
+    FIX_SUMMARY: [what bug was fixed and how]
+    FILES_CHANGED: [list of files]
+    RISK: NONE
+
+IF ANY CONDITION NOT MET:
+  Report back with:
+    ACTION: NEEDS_HUMAN_DECISION
+    FIX_SUMMARY: [what the PR does]
+    WHAT_IT_FIXES: [the bug or issue it addresses]
+    CI_STATUS: [PASS | FAIL | PENDING — list any failures]
+    REVIEW_STATUS: [APPROVED | CHANGES_REQUESTED | PENDING | NONE]
+    MISSING: [what's preventing auto-merge — be specific]
+    RISK_ASSESSMENT: [what could go wrong]
+    AMBIGUOUS_PARTS: [anything that needs human judgment]
+    RECOMMENDED_ACTION: [what the maintainer should do]
+
+ABSOLUTE RULES:
+- NEVER run `git checkout`, `git fetch`, `git pull`, or `git switch`. READ-ONLY via gh CLI and API.
+- NEVER checkout the PR branch. NEVER. Use `gh api` and `gh pr view` only.
+- Only merge if you are 100% certain ALL conditions are met. When in doubt, report instead.
+- The [sisyphus-bot] prefix is MANDATORY on any comment you post.
+```
+
+</pr_bugfix_prompt>
+
+---
+
+### SUBAGENT_PR_OTHER
+
+<pr_other_prompt>
+
+```
+You are a GitHub PR reviewer for the repository {REPO}.
+
+ITEM:
+- PR #{number}: {title}
+- Author: {author}
+- Base: {baseRefName}
+- Head: {headRefName}
+- Draft: {isDraft}
+- Mergeable: {mergeable}
+- Review Decision: {reviewDecision}
+- CI Status: {statusCheckRollup_summary}
+- Body: {body}
+
+YOUR JOB:
+1. Fetch PR details (READ-ONLY — no checkout):
+   gh pr view {number} --repo {REPO} --json files,reviews,comments,statusCheckRollup,reviewDecision
+2. Read the changed files via `gh api repos/{REPO}/pulls/{number}/files`.
+3. Assess the PR and report:
+
+  ACTION: PR_ASSESSED
+  TYPE: [FEATURE | REFACTOR | DOCS | CHORE | TEST | OTHER]
+  SUMMARY: [what this PR does in 2-3 sentences]
+  CI_STATUS: [PASS | FAIL | PENDING]
+  REVIEW_STATUS: [APPROVED | CHANGES_REQUESTED | PENDING | NONE]
+  FILES_CHANGED: [count and key files]
+  RISK_LEVEL: [LOW | MEDIUM | HIGH]
+  ALIGNMENT: [does this fit the project direction? YES | NO | UNCLEAR]
+  BLOCKERS: [anything preventing merge]
+  RECOMMENDED_ACTION: [MERGE | REQUEST_CHANGES | NEEDS_REVIEW | CLOSE | WAIT]
+  NOTES: [any observations for the maintainer]
+
+ABSOLUTE RULES:
+- NEVER run `git checkout`, `git fetch`, `git pull`, or `git switch`. READ-ONLY.
+- NEVER checkout the PR branch. Use `gh api` and `gh pr view` only.
+- Do NOT merge non-bugfix PRs automatically. Report only.
+```
+
+</pr_other_prompt>
+
+---
+
+## PHASE 4: COLLECT RESULTS & UPDATE TASKS
+
+<collection>
+Poll `background_output()` for each spawned task. As each completes:
+
+1. Parse the subagent's report.
+2. Update the corresponding TaskCreate entry:
+   - `TaskUpdate(id=task_id, status="completed", description=FULL_REPORT_TEXT)`
+3. Stream the result to the user immediately — do not wait for all to finish.
+
+Track counters:
+- issues_answered (commented + closed)
+- bugs_confirmed
+- bugs_not_a_bug
+- prs_merged
+- prs_needs_decision
+- features_assessed
+</collection>
+
+---
+
+## PHASE 5: FINAL SUMMARY
+
+After all background tasks complete, produce a summary:
+
+```markdown
+# GitHub Triage Report — {REPO}
+
+**Date:** {date}
+**Items Processed:** {total}
+
+## Issues ({issue_count})
+| Action | Count |
+|--------|-------|
+| Answered & Closed | {issues_answered} |
+| Bug Confirmed | {bugs_confirmed} |
+| Not A Bug (explained) | {bugs_not_a_bug} |
+| Feature Assessed | {features_assessed} |
+| Needs Manual Attention | {needs_manual} |
+
+## PRs ({pr_count})
+| Action | Count |
+|--------|-------|
+| Auto-Merged (safe bugfix) | {prs_merged} |
+| Needs Human Decision | {prs_needs_decision} |
+| Assessed (non-bugfix) | {prs_assessed} |
+
+## Items Requiring Your Attention
+[List each item that needs human decision with its report summary]
+```
+
+---
+
+## ANTI-PATTERNS
+
+| Violation | Severity |
+|-----------|----------|
+| Using any category other than `free` | CRITICAL |
+| Batching multiple items into one task | CRITICAL |
+| Using `run_in_background=false` | CRITICAL |
+| Subagent running `git checkout` on a PR branch | CRITICAL |
+| Posting comment without `[sisyphus-bot]` prefix | CRITICAL |
+| Merging a PR that doesn't meet ALL 6 conditions | CRITICAL |
+| Closing a bug issue (only comment, never close bugs) | HIGH |
+| Guessing at answers without codebase evidence | HIGH |
+| Not recording results via TaskCreate/TaskUpdate | HIGH |
+
+---
+
+## QUICK START
+
+When invoked:
+
+1. `TaskCreate` for the overall triage job
+2. Fetch all open issues + PRs via gh CLI (paginate if needed)
+3. Classify each item (ISSUE_QUESTION, ISSUE_BUG, ISSUE_FEATURE, PR_BUGFIX, etc.)
+4. For EACH item: `TaskCreate` + `task(category="free", run_in_background=true, load_skills=[], prompt=...)`
+5. Poll `background_output()` — stream results as they arrive
+6. `TaskUpdate` each task with the subagent's findings
+7. Produce final summary report

.opencode/skills/github-triage/scripts/gh_fetch.py

@@ -69,7 +69,9 @@ async def run_gh_command(args: list[str]) -> tuple[str, str, int]:
 
 async def get_current_repo() -> str:
     """Get the current repository from gh CLI."""
-    stdout, stderr, code = await run_gh_command(["repo", "view", "--json", "nameWithOwner", "-q", ".nameWithOwner"])
+    stdout, stderr, code = await run_gh_command(
+        ["repo", "view", "--json", "nameWithOwner", "-q", ".nameWithOwner"]
+    )
     if code != 0:
         console.print(f"[red]Error getting current repo: {stderr}[/red]")
         raise typer.Exit(1)
@@ -123,7 +125,6 @@ async def fetch_all_items(
     all_items: list[dict] = []
     page = 1
 
-    # First fetch
     progress.update(task_id, description=f"[cyan]Fetching {item_type}s page {page}...")
     items = await fetch_items_page(repo, item_type, state, BATCH_SIZE)
     fetched_count = len(items)
@@ -131,24 +132,25 @@ async def fetch_all_items(
 
     console.print(f"[dim]Page {page}: fetched {fetched_count} {item_type}s[/dim]")
 
-    # Continue pagination if we got exactly BATCH_SIZE (more pages exist)
     while fetched_count == BATCH_SIZE:
         page += 1
-        progress.update(task_id, description=f"[cyan]Fetching {item_type}s page {page}...")
+        progress.update(
+            task_id, description=f"[cyan]Fetching {item_type}s page {page}..."
+        )
 
-        # Use created date of last item to paginate
         last_created = all_items[-1].get("createdAt", "")
         if not last_created:
             break
 
         search_filter = f"created:<{last_created}"
-        items = await fetch_items_page(repo, item_type, state, BATCH_SIZE, search_filter)
+        items = await fetch_items_page(
+            repo, item_type, state, BATCH_SIZE, search_filter
+        )
         fetched_count = len(items)
 
         if fetched_count == 0:
             break
 
-        # Deduplicate by number
         existing_numbers = {item["number"] for item in all_items}
         new_items = [item for item in items if item["number"] not in existing_numbers]
         all_items.extend(new_items)
@@ -157,12 +159,10 @@ async def fetch_all_items(
             f"[dim]Page {page}: fetched {fetched_count}, added {len(new_items)} new (total: {len(all_items)})[/dim]"
         )
 
-        # Safety limit
         if page > 20:
             console.print("[yellow]Safety limit reached (20 pages)[/yellow]")
             break
 
-    # Filter by time if specified
     if hours is not None:
         cutoff = datetime.now(UTC) - timedelta(hours=hours)
         cutoff_str = cutoff.isoformat()
@@ -171,11 +171,14 @@ async def fetch_all_items(
         all_items = [
             item
             for item in all_items
-            if item.get("createdAt", "") >= cutoff_str or item.get("updatedAt", "") >= cutoff_str
+            if item.get("createdAt", "") >= cutoff_str
+            or item.get("updatedAt", "") >= cutoff_str
         ]
         filtered_count = original_count - len(all_items)
         if filtered_count > 0:
-            console.print(f"[dim]Filtered out {filtered_count} items older than {hours} hours[/dim]")
+            console.print(
+                f"[dim]Filtered out {filtered_count} items older than {hours} hours[/dim]"
+            )
 
     return all_items
 
@@ -190,14 +193,16 @@ def display_table(items: list[dict], item_type: str) -> None:
     table.add_column("Labels", style="magenta", max_width=30)
     table.add_column("Updated", style="dim", width=12)
 
-    for item in items[:50]:  # Show first 50
+    for item in items[:50]:
         labels = ", ".join(label.get("name", "") for label in item.get("labels", []))
         updated = item.get("updatedAt", "")[:10]
         author = item.get("author", {}).get("login", "unknown")
 
         table.add_row(
             str(item.get("number", "")),
-            (item.get("title", "")[:47] + "...") if len(item.get("title", "")) > 50 else item.get("title", ""),
+            (item.get("title", "")[:47] + "...")
+            if len(item.get("title", "")) > 50
+            else item.get("title", ""),
             item.get("state", ""),
             author,
             (labels[:27] + "...") if len(labels) > 30 else labels,
@@ -211,13 +216,21 @@ def display_table(items: list[dict], item_type: str) -> None:
 
 @app.command()
 def issues(
-    repo: Annotated[str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")] = None,
-    state: Annotated[ItemState, typer.Option("--state", "-s", help="Issue state filter")] = ItemState.ALL,
+    repo: Annotated[
+        str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")
+    ] = None,
+    state: Annotated[
+        ItemState, typer.Option("--state", "-s", help="Issue state filter")
+    ] = ItemState.ALL,
     hours: Annotated[
         int | None,
-        typer.Option("--hours", "-h", help="Only issues from last N hours (created or updated)"),
+        typer.Option(
+            "--hours", "-h", help="Only issues from last N hours (created or updated)"
+        ),
     ] = None,
-    output: Annotated[OutputFormat, typer.Option("--output", "-o", help="Output format")] = OutputFormat.TABLE,
+    output: Annotated[
+        OutputFormat, typer.Option("--output", "-o", help="Output format")
+    ] = OutputFormat.TABLE,
 ) -> None:
     """Fetch all issues with exhaustive pagination."""
 
@@ -225,33 +238,29 @@ def issues(
         target_repo = repo or await get_current_repo()
 
         console.print(f"""
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
 [cyan]Repository:[/cyan] {target_repo}
 [cyan]State:[/cyan] {state.value}
 [cyan]Time filter:[/cyan] {f"Last {hours} hours" if hours else "All time"}
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
 """)
 
         with Progress(console=console) as progress:
             task: TaskID = progress.add_task("[cyan]Fetching issues...", total=None)
-
-            items = await fetch_all_items(target_repo, "issue", state.value, hours, progress, task)
-
-            progress.update(task, description="[green]Complete!", completed=100, total=100)
+            items = await fetch_all_items(
+                target_repo, "issue", state.value, hours, progress, task
+            )
+            progress.update(
+                task, description="[green]Complete!", completed=100, total=100
+            )
 
         console.print(
-            Panel(
-                f"[green]✓ Found {len(items)} issues[/green]",
-                title="[green]Pagination Complete[/green]",
-                border_style="green",
-            )
+            Panel(f"[green]Found {len(items)} issues[/green]", border_style="green")
         )
 
         if output == OutputFormat.JSON:
             console.print(json.dumps(items, indent=2, ensure_ascii=False))
         elif output == OutputFormat.TABLE:
             display_table(items, "issue")
-        else:  # COUNT
+        else:
             console.print(f"Total issues: {len(items)}")
 
     asyncio.run(async_main())
@@ -259,13 +268,21 @@ def issues(
 
 @app.command()
 def prs(
-    repo: Annotated[str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")] = None,
-    state: Annotated[ItemState, typer.Option("--state", "-s", help="PR state filter")] = ItemState.OPEN,
+    repo: Annotated[
+        str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")
+    ] = None,
+    state: Annotated[
+        ItemState, typer.Option("--state", "-s", help="PR state filter")
+    ] = ItemState.OPEN,
     hours: Annotated[
         int | None,
-        typer.Option("--hours", "-h", help="Only PRs from last N hours (created or updated)"),
+        typer.Option(
+            "--hours", "-h", help="Only PRs from last N hours (created or updated)"
+        ),
     ] = None,
-    output: Annotated[OutputFormat, typer.Option("--output", "-o", help="Output format")] = OutputFormat.TABLE,
+    output: Annotated[
+        OutputFormat, typer.Option("--output", "-o", help="Output format")
+    ] = OutputFormat.TABLE,
 ) -> None:
     """Fetch all PRs with exhaustive pagination."""
 
@@ -273,33 +290,29 @@ def prs(
         target_repo = repo or await get_current_repo()
 
         console.print(f"""
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
 [cyan]Repository:[/cyan] {target_repo}
 [cyan]State:[/cyan] {state.value}
 [cyan]Time filter:[/cyan] {f"Last {hours} hours" if hours else "All time"}
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
 """)
 
         with Progress(console=console) as progress:
             task: TaskID = progress.add_task("[cyan]Fetching PRs...", total=None)
-
-            items = await fetch_all_items(target_repo, "pr", state.value, hours, progress, task)
-
-            progress.update(task, description="[green]Complete!", completed=100, total=100)
+            items = await fetch_all_items(
+                target_repo, "pr", state.value, hours, progress, task
+            )
+            progress.update(
+                task, description="[green]Complete!", completed=100, total=100
+            )
 
         console.print(
-            Panel(
-                f"[green]✓ Found {len(items)} PRs[/green]",
-                title="[green]Pagination Complete[/green]",
-                border_style="green",
-            )
+            Panel(f"[green]Found {len(items)} PRs[/green]", border_style="green")
         )
 
         if output == OutputFormat.JSON:
             console.print(json.dumps(items, indent=2, ensure_ascii=False))
         elif output == OutputFormat.TABLE:
             display_table(items, "pr")
-        else:  # COUNT
+        else:
             console.print(f"Total PRs: {len(items)}")
 
     asyncio.run(async_main())
@@ -307,13 +320,21 @@ def prs(
 
 @app.command(name="all")
 def fetch_all(
-    repo: Annotated[str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")] = None,
-    state: Annotated[ItemState, typer.Option("--state", "-s", help="State filter")] = ItemState.ALL,
+    repo: Annotated[
+        str | None, typer.Option("--repo", "-r", help="Repository (owner/repo)")
+    ] = None,
+    state: Annotated[
+        ItemState, typer.Option("--state", "-s", help="State filter")
+    ] = ItemState.ALL,
     hours: Annotated[
         int | None,
-        typer.Option("--hours", "-h", help="Only items from last N hours (created or updated)"),
+        typer.Option(
+            "--hours", "-h", help="Only items from last N hours (created or updated)"
+        ),
     ] = None,
-    output: Annotated[OutputFormat, typer.Option("--output", "-o", help="Output format")] = OutputFormat.TABLE,
+    output: Annotated[
+        OutputFormat, typer.Option("--output", "-o", help="Output format")
+    ] = OutputFormat.TABLE,
 ) -> None:
     """Fetch all issues AND PRs with exhaustive pagination."""
 
@@ -321,22 +342,25 @@ def fetch_all(
         target_repo = repo or await get_current_repo()
 
         console.print(f"""
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
 [cyan]Repository:[/cyan] {target_repo}
 [cyan]State:[/cyan] {state.value}
 [cyan]Time filter:[/cyan] {f"Last {hours} hours" if hours else "All time"}
 [cyan]Fetching:[/cyan] Issues AND PRs
-[cyan]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/cyan]
 """)
 
         with Progress(console=console) as progress:
-            issues_task: TaskID = progress.add_task("[cyan]Fetching issues...", total=None)
+            issues_task: TaskID = progress.add_task(
+                "[cyan]Fetching issues...", total=None
+            )
             prs_task: TaskID = progress.add_task("[cyan]Fetching PRs...", total=None)
 
-            # Fetch in parallel
             issues_items, prs_items = await asyncio.gather(
-                fetch_all_items(target_repo, "issue", state.value, hours, progress, issues_task),
-                fetch_all_items(target_repo, "pr", state.value, hours, progress, prs_task),
+                fetch_all_items(
+                    target_repo, "issue", state.value, hours, progress, issues_task
+                ),
+                fetch_all_items(
+                    target_repo, "pr", state.value, hours, progress, prs_task
+                ),
             )
 
             progress.update(
@@ -345,12 +369,13 @@ def fetch_all(
                 completed=100,
                 total=100,
             )
-            progress.update(prs_task, description="[green]PRs complete!", completed=100, total=100)
+            progress.update(
+                prs_task, description="[green]PRs complete!", completed=100, total=100
+            )
 
         console.print(
             Panel(
-                f"[green]✓ Found {len(issues_items)} issues and {len(prs_items)} PRs[/green]",
-                title="[green]Pagination Complete[/green]",
+                f"[green]Found {len(issues_items)} issues and {len(prs_items)} PRs[/green]",
                 border_style="green",
             )
         )
@@ -362,7 +387,7 @@ def fetch_all(
             display_table(issues_items, "issue")
             console.print("")
             display_table(prs_items, "pr")
-        else:  # COUNT
+        else:
             console.print(f"Total issues: {len(issues_items)}")
             console.print(f"Total PRs: {len(prs_items)}")
 

AGENTS.md

@@ -1,10 +1,10 @@
 # oh-my-opencode — OpenCode Plugin
 
-**Generated:** 2026-02-17 | **Commit:** aac79f03 | **Branch:** dev
+**Generated:** 2026-02-18 | **Commit:** 04e95d7e | **Branch:** dev
 
 ## OVERVIEW
 
-OpenCode plugin (npm: `oh-my-opencode`) that extends Claude Code (OpenCode fork) with multi-agent orchestration, 41 lifecycle hooks, 26 tools, skill/command/MCP systems, and Claude Code compatibility. 1164 TypeScript files, 133k LOC.
+OpenCode plugin (npm: `oh-my-opencode`) that extends Claude Code (OpenCode fork) with multi-agent orchestration, 44 lifecycle hooks, 26 tools, skill/command/MCP systems, and Claude Code compatibility. 1149 TypeScript files, 132k LOC.
 
 ## STRUCTURE
 
@@ -14,14 +14,14 @@ oh-my-opencode/
 │   ├── index.ts              # Plugin entry: loadConfig → createManagers → createTools → createHooks → createPluginInterface
 │   ├── plugin-config.ts      # JSONC multi-level config: user → project → defaults (Zod v4)
 │   ├── agents/               # 11 agents (Sisyphus, Hephaestus, Oracle, Librarian, Explore, Atlas, Prometheus, Metis, Momus, Multimodal-Looker, Sisyphus-Junior)
-│   ├── hooks/                # 41 hooks across 37 directories + 6 standalone files
+│   ├── hooks/                # 44 hooks across 39 directories + 6 standalone files
 │   ├── tools/                # 26 tools across 15 directories
-│   ├── features/             # 18 feature modules (background-agent, skill-loader, tmux, MCP-OAuth, etc.)
+│   ├── features/             # 19 feature modules (background-agent, skill-loader, tmux, MCP-OAuth, etc.)
 │   ├── shared/               # 101 utility files in 13 categories
 │   ├── config/               # Zod v4 schema system (22 files)
 │   ├── cli/                  # CLI: install, run, doctor, mcp-oauth (Commander.js)
 │   ├── mcp/                  # 3 built-in remote MCPs (websearch, context7, grep_app)
-│   ├── plugin/               # 8 OpenCode hook handlers + 41 hook composition
+│   ├── plugin/               # 8 OpenCode hook handlers + 44 hook composition
 │   └── plugin-handlers/      # 6-phase config loading pipeline
 ├── packages/                 # Monorepo: comment-checker, opencode-sdk
 └── local-ignore/             # Dev-only test fixtures
@@ -34,7 +34,7 @@ OhMyOpenCodePlugin(ctx)
   ├─→ loadPluginConfig()         # JSONC parse → project/user merge → Zod validate → migrate
   ├─→ createManagers()           # TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler
   ├─→ createTools()              # SkillContext + AvailableCategories + ToolRegistry (26 tools)
-  ├─→ createHooks()              # 3-tier: Core(32) + Continuation(7) + Skill(2) = 41 hooks
+  ├─→ createHooks()              # 3-tier: Core(35) + Continuation(7) + Skill(2) = 44 hooks
   └─→ createPluginInterface()    # 8 OpenCode hook handlers → PluginInterface
 ```
 
@@ -86,7 +86,7 @@ Fields: agents (14 overridable), categories (8 built-in + custom), disabled_* ar
 
 - **Test pattern**: Vitest, co-located `*.test.ts`, given/when/then style
 - **Factory pattern**: `createXXX()` for all tools, hooks, agents
-- **Hook tiers**: Session (19) → Tool-Guard (9) → Transform (4) → Continuation (7) → Skill (2)
+- **Hook tiers**: Session (22) → Tool-Guard (9) → Transform (4) → Continuation (7) → Skill (2)
 - **Agent modes**: `primary` (respects UI model) vs `subagent` (own fallback chain) vs `all`
 - **Model resolution**: 3-step: override → category-default → provider-fallback → system-default
 - **Config format**: JSONC with comments, Zod v4 validation, snake_case keys

assets/oh-my-opencode.schema.json

@@ -87,9 +87,11 @@
           "claude-code-hooks",
           "auto-slash-command",
           "edit-error-recovery",
+          "json-error-recovery",
           "delegate-task-retry",
           "prometheus-md-only",
           "sisyphus-junior-notepad",
+          "sisyphus-gpt-hephaestus-reminder",
           "start-work",
           "atlas",
           "unstable-agent-babysitter",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -74,13 +74,13 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.7.1",
-    "oh-my-opencode-darwin-x64": "3.7.1",
-    "oh-my-opencode-linux-arm64": "3.7.1",
-    "oh-my-opencode-linux-arm64-musl": "3.7.1",
-    "oh-my-opencode-linux-x64": "3.7.1",
-    "oh-my-opencode-linux-x64-musl": "3.7.1",
-    "oh-my-opencode-windows-x64": "3.7.1"
+    "oh-my-opencode-darwin-arm64": "3.7.3",
+    "oh-my-opencode-darwin-x64": "3.7.3",
+    "oh-my-opencode-linux-arm64": "3.7.3",
+    "oh-my-opencode-linux-arm64-musl": "3.7.3",
+    "oh-my-opencode-linux-x64": "3.7.3",
+    "oh-my-opencode-linux-x64-musl": "3.7.3",
+    "oh-my-opencode-windows-x64": "3.7.3"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.7.1",
+  "version": "3.7.3",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

signatures/cla.json

@@ -1527,6 +1527,38 @@
       "created_at": "2026-02-16T19:01:33Z",
       "repoId": 1108837393,
       "pullRequestNo": 1906
+    },
+    {
+      "name": "feelsodev",
+      "id": 59601439,
+      "comment_id": 3914425492,
+      "created_at": "2026-02-17T12:24:00Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1917
+    },
+    {
+      "name": "rentiansheng",
+      "id": 3955934,
+      "comment_id": 3914953522,
+      "created_at": "2026-02-17T14:18:29Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1889
+    },
+    {
+      "name": "codeg-dev",
+      "id": 12405078,
+      "comment_id": 3915482750,
+      "created_at": "2026-02-17T15:47:18Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1927
+    },
+    {
+      "name": "codeg-dev",
+      "id": 12405078,
+      "comment_id": 3915952929,
+      "created_at": "2026-02-17T17:11:11Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1927
     }
   ]
 }

src/AGENTS.md

@@ -1,6 +1,6 @@
 # src/ — Plugin Source
 
-**Generated:** 2026-02-17
+**Generated:** 2026-02-18
 
 ## OVERVIEW
 
@@ -14,7 +14,7 @@ Root source directory. Entry point `index.ts` orchestrates 4-step initialization
 | `plugin-config.ts` | JSONC parse, multi-level merge (user → project → defaults), Zod validation |
 | `create-managers.ts` | TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler |
 | `create-tools.ts` | SkillContext + AvailableCategories + ToolRegistry |
-| `create-hooks.ts` | 3-tier hook composition: Core(32) + Continuation(7) + Skill(2) |
+| `create-hooks.ts` | 3-tier hook composition: Core(35) + Continuation(7) + Skill(2) |
 | `plugin-interface.ts` | Assembles 8 OpenCode hook handlers into PluginInterface |
 
 ## CONFIG LOADING
@@ -32,8 +32,8 @@ loadPluginConfig(directory, ctx)
 
 ```
 createHooks()
-  ├─→ createCoreHooks()           # 32 hooks
-  │   ├─ createSessionHooks()     # 19: contextWindowMonitor, thinkMode, ralphLoop, sessionRecovery...
+  ├─→ createCoreHooks()           # 35 hooks
+  │   ├─ createSessionHooks()     # 22: contextWindowMonitor, thinkMode, ralphLoop, sessionRecovery, jsonErrorRecovery, sisyphusGptHephaestusReminder, taskReminder...
   │   ├─ createToolGuardHooks()   # 9: commentChecker, rulesInjector, writeExistingFileGuard...
   │   └─ createTransformHooks()   # 4: claudeCodeHooks, keywordDetector, contextInjector, thinkingBlockValidator
   ├─→ createContinuationHooks()   # 7: todoContinuationEnforcer, atlas, stopContinuationGuard...

src/agents/prometheus/identity-constraints.ts

@@ -166,40 +166,71 @@ unblocking maximum parallelism in subsequent waves.
 
 **The plan can have 50+ TODOs. That's OK. ONE PLAN.**
 
-### 6.1 SINGLE ATOMIC WRITE (CRITICAL - Prevents Content Loss)
+### 6.1 INCREMENTAL WRITE PROTOCOL (CRITICAL - Prevents Output Limit Stalls)
 
 <write_protocol>
-**The Write tool OVERWRITES files. It does NOT append.**
+**Write OVERWRITES. Never call Write twice on the same file.**
 
-**MANDATORY PROTOCOL:**
-1. **Prepare ENTIRE plan content in memory FIRST**
-2. **Write ONCE with complete content**
-3. **NEVER split into multiple Write calls**
+Plans with many tasks will exceed your output token limit if you try to generate everything at once.
+Split into: **one Write** (skeleton) + **multiple Edits** (tasks in batches).
 
-**IF plan is too large for single output:**
-1. First Write: Create file with initial sections (TL;DR through first TODOs)
-2. Subsequent: Use **Edit tool** to APPEND remaining sections
-   - Target the END of the file
-   - Edit replaces text, so include last line + new content
+**Step 1 — Write skeleton (all sections EXCEPT individual task details):**
 
-**FORBIDDEN (causes content loss):**
 \`\`\`
-❌ Write(".sisyphus/plans/x.md", "# Part 1...")  
-❌ Write(".sisyphus/plans/x.md", "# Part 2...")  // Part 1 is GONE!
+Write(".sisyphus/plans/{name}.md", content=\`
+# {Plan Title}
+
+## TL;DR
+> ...
+
+## Context
+...
+
+## Work Objectives
+...
+
+## Verification Strategy
+...
+
+## Execution Strategy
+...
+
+---
+
+## TODOs
+
+---
+
+## Final Verification Wave
+...
+
+## Commit Strategy
+...
+
+## Success Criteria
+...
+\`)
 \`\`\`
 
-**CORRECT (preserves content):**
-\`\`\`
-✅ Write(".sisyphus/plans/x.md", "# Complete plan content...")  // Single write
+**Step 2 — Edit-append tasks in batches of 2-4:**
 
-// OR if too large:
-✅ Write(".sisyphus/plans/x.md", "# Plan\n## TL;DR\n...")  // First chunk
-✅ Edit(".sisyphus/plans/x.md", oldString="---\n## Success Criteria", newString="---\n## More TODOs\n...\n---\n## Success Criteria")  // Append via Edit
+Use Edit to insert each batch of tasks before the Final Verification section:
+
+\`\`\`
+Edit(".sisyphus/plans/{name}.md",
+  oldString="---\\n\\n## Final Verification Wave",
+  newString="- [ ] 1. Task Title\\n\\n  **What to do**: ...\\n  **QA Scenarios**: ...\\n\\n- [ ] 2. Task Title\\n\\n  **What to do**: ...\\n  **QA Scenarios**: ...\\n\\n---\\n\\n## Final Verification Wave")
 \`\`\`
 
-**SELF-CHECK before Write:**
-- [ ] Is this the FIRST write to this file? → Write is OK
-- [ ] File already exists with my content? → Use Edit to append, NOT Write
+Repeat until all tasks are written. 2-4 tasks per Edit call balances speed and output limits.
+
+**Step 3 — Verify completeness:**
+
+After all Edits, Read the plan file to confirm all tasks are present and no content was lost.
+
+**FORBIDDEN:**
+- \`Write()\` twice to the same file — second call erases the first
+- Generating ALL tasks in a single Write — hits output limits, causes stalls
 </write_protocol>
 
 ### 7. DRAFT AS WORKING MEMORY (MANDATORY)

src/cli/cli-program.ts

@@ -67,20 +67,19 @@ program
    .command("run <message>")
    .allowUnknownOption()
    .passThroughOptions()
-   .description("Run opencode with todo/background task completion enforcement")
+  .description("Run opencode with todo/background task completion enforcement")
   .option("-a, --agent <name>", "Agent to use (default: from CLI/env/config, fallback: Sisyphus)")
   .option("-d, --directory <path>", "Working directory")
-  .option("-t, --timeout <ms>", "Timeout in milliseconds (default: 30 minutes)", parseInt)
   .option("-p, --port <port>", "Server port (attaches if port already in use)", parseInt)
   .option("--attach <url>", "Attach to existing opencode server URL")
   .option("--on-complete <command>", "Shell command to run after completion")
   .option("--json", "Output structured JSON result to stdout")
+  .option("--verbose", "Show full event stream (default: messages/tools only)")
   .option("--session-id <id>", "Resume existing session instead of creating new one")
   .addHelpText("after", `
 Examples:
   $ bunx oh-my-opencode run "Fix the bug in index.ts"
   $ bunx oh-my-opencode run --agent Sisyphus "Implement feature X"
-  $ bunx oh-my-opencode run --timeout 3600000 "Large refactoring task"
   $ bunx oh-my-opencode run --port 4321 "Fix the bug"
   $ bunx oh-my-opencode run --attach http://127.0.0.1:4321 "Fix the bug"
   $ bunx oh-my-opencode run --json "Fix the bug" | jq .sessionId
@@ -109,11 +108,11 @@ Unlike 'opencode run', this command waits until:
       message,
       agent: options.agent,
       directory: options.directory,
-      timeout: options.timeout,
       port: options.port,
       attach: options.attach,
       onComplete: options.onComplete,
       json: options.json ?? false,
+      verbose: options.verbose ?? false,
       sessionId: options.sessionId,
     }
     const exitCode = await run(runOptions)

src/cli/run/AGENTS.md

@@ -0,0 +1,56 @@
+# src/cli/run/ — Non-Interactive Session Launcher
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+37 files. Powers the `oh-my-opencode run <message>` command. Connects to OpenCode server, creates/resumes sessions, streams events, and polls for completion.
+
+## EXECUTION FLOW
+
+```
+runner.ts
+  1. opencode-binary-resolver.ts → Find OpenCode binary
+  2. server-connection.ts → Connect to OpenCode server (start if needed)
+  3. agent-resolver.ts → Flag → env → config → Sisyphus
+  4. session-resolver.ts → Create new or resume existing session
+  5. events.ts → Stream SSE events from session
+  6. event-handlers.ts → Process each event type
+  7. poll-for-completion.ts → Wait for todos + background tasks done
+  8. on-complete-hook.ts → Execute user-defined completion hook
+```
+
+## KEY FILES
+
+| File | Purpose |
+|------|---------|
+| `runner.ts` | Main orchestration — connects, resolves, runs, completes |
+| `server-connection.ts` | Start OpenCode server process, create SDK client |
+| `agent-resolver.ts` | Resolve agent: `--agent` flag → `OPENCODE_AGENT` env → config → Sisyphus |
+| `session-resolver.ts` | Create new session or resume via `--attach` / `--session-id` |
+| `events.ts` | SSE event stream subscription |
+| `event-handlers.ts` | Route events to handlers (message, tool, error, idle) |
+| `event-stream-processor.ts` | Process event stream with filtering and buffering |
+| `poll-for-completion.ts` | Poll session until todos complete + no background tasks |
+| `completion.ts` | Determine if session is truly done |
+| `continuation-state.ts` | Persist state for `run` continuation across invocations |
+| `output-renderer.ts` | Format session output for terminal |
+| `json-output.ts` | JSON output mode (`--json` flag) |
+| `types.ts` | `RunOptions`, `RunResult`, `RunContext`, event payload types |
+
+## AGENT RESOLUTION PRIORITY
+
+```
+1. --agent CLI flag
+2. OPENCODE_AGENT environment variable
+3. default_run_agent config
+4. "sisyphus" (default)
+```
+
+## COMPLETION DETECTION
+
+Poll-based with two conditions:
+1. All todos marked completed (no pending/in_progress)
+2. No running background tasks
+
+`on-complete-hook.ts` executes optional user command on completion (e.g., `--on-complete "notify-send done"`).

src/cli/run/agent-profile-colors.ts

@@ -0,0 +1,28 @@
+import type { OpencodeClient } from "@opencode-ai/sdk"
+import { normalizeSDKResponse } from "../../shared"
+
+interface AgentProfile {
+  name?: string
+  color?: string
+}
+
+export async function loadAgentProfileColors(
+  client: OpencodeClient,
+): Promise<Record<string, string>> {
+  try {
+    const agentsRes = await client.app.agents()
+    const agents = normalizeSDKResponse(agentsRes, [] as AgentProfile[], {
+      preferResponseOnMissingData: true,
+    })
+
+    const colors: Record<string, string> = {}
+    for (const agent of agents) {
+      if (!agent.name || !agent.color) continue
+      colors[agent.name] = agent.color
+    }
+
+    return colors
+  } catch {
+    return {}
+  }
+}

src/cli/run/completion-continuation.test.ts

@@ -0,0 +1,138 @@
+import { describe, it, expect, mock, spyOn, afterEach } from "bun:test"
+import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from "node:fs"
+import { join } from "node:path"
+import { tmpdir } from "node:os"
+import type { RunContext } from "./types"
+import { writeState as writeRalphLoopState } from "../../hooks/ralph-loop/storage"
+
+const testDirs: string[] = []
+
+afterEach(() => {
+  while (testDirs.length > 0) {
+    const dir = testDirs.pop()
+    if (dir) {
+      rmSync(dir, { recursive: true, force: true })
+    }
+  }
+})
+
+function createTempDir(): string {
+  const dir = mkdtempSync(join(tmpdir(), "omo-run-continuation-"))
+  testDirs.push(dir)
+  return dir
+}
+
+function createMockContext(directory: string): RunContext {
+  return {
+    client: {
+      session: {
+        todo: mock(() => Promise.resolve({ data: [] })),
+        children: mock(() => Promise.resolve({ data: [] })),
+        status: mock(() => Promise.resolve({ data: {} })),
+      },
+    } as unknown as RunContext["client"],
+    sessionID: "test-session",
+    directory,
+    abortController: new AbortController(),
+  }
+}
+
+function writeBoulderStateFile(directory: string, activePlanPath: string, sessionIDs: string[]): void {
+  const sisyphusDir = join(directory, ".sisyphus")
+  mkdirSync(sisyphusDir, { recursive: true })
+  writeFileSync(
+    join(sisyphusDir, "boulder.json"),
+    JSON.stringify({
+      active_plan: activePlanPath,
+      started_at: new Date().toISOString(),
+      session_ids: sessionIDs,
+      plan_name: "test-plan",
+      agent: "atlas",
+    }),
+    "utf-8",
+  )
+}
+
+describe("checkCompletionConditions continuation coverage", () => {
+  it("returns false when active boulder continuation exists for this session", async () => {
+    // given
+    spyOn(console, "log").mockImplementation(() => {})
+    const directory = createTempDir()
+    const planPath = join(directory, ".sisyphus", "plans", "active-plan.md")
+    mkdirSync(join(directory, ".sisyphus", "plans"), { recursive: true })
+    writeFileSync(planPath, "- [ ] incomplete task\n", "utf-8")
+    writeBoulderStateFile(directory, planPath, ["test-session"])
+    const ctx = createMockContext(directory)
+    const { checkCompletionConditions } = await import("./completion")
+
+    // when
+    const result = await checkCompletionConditions(ctx)
+
+    // then
+    expect(result).toBe(false)
+  })
+
+  it("returns true when boulder exists but is complete", async () => {
+    // given
+    spyOn(console, "log").mockImplementation(() => {})
+    const directory = createTempDir()
+    const planPath = join(directory, ".sisyphus", "plans", "done-plan.md")
+    mkdirSync(join(directory, ".sisyphus", "plans"), { recursive: true })
+    writeFileSync(planPath, "- [x] completed task\n", "utf-8")
+    writeBoulderStateFile(directory, planPath, ["test-session"])
+    const ctx = createMockContext(directory)
+    const { checkCompletionConditions } = await import("./completion")
+
+    // when
+    const result = await checkCompletionConditions(ctx)
+
+    // then
+    expect(result).toBe(true)
+  })
+
+  it("returns false when active ralph-loop continuation exists for this session", async () => {
+    // given
+    spyOn(console, "log").mockImplementation(() => {})
+    const directory = createTempDir()
+    writeRalphLoopState(directory, {
+      active: true,
+      iteration: 2,
+      max_iterations: 10,
+      completion_promise: "DONE",
+      started_at: new Date().toISOString(),
+      prompt: "keep going",
+      session_id: "test-session",
+    })
+    const ctx = createMockContext(directory)
+    const { checkCompletionConditions } = await import("./completion")
+
+    // when
+    const result = await checkCompletionConditions(ctx)
+
+    // then
+    expect(result).toBe(false)
+  })
+
+  it("returns true when active ralph-loop is bound to another session", async () => {
+    // given
+    spyOn(console, "log").mockImplementation(() => {})
+    const directory = createTempDir()
+    writeRalphLoopState(directory, {
+      active: true,
+      iteration: 2,
+      max_iterations: 10,
+      completion_promise: "DONE",
+      started_at: new Date().toISOString(),
+      prompt: "keep going",
+      session_id: "other-session",
+    })
+    const ctx = createMockContext(directory)
+    const { checkCompletionConditions } = await import("./completion")
+
+    // when
+    const result = await checkCompletionConditions(ctx)
+
+    // then
+    expect(result).toBe(true)
+  })
+})

src/cli/run/completion.test.ts

@@ -143,6 +143,47 @@ describe("checkCompletionConditions", () => {
     expect(result).toBe(false)
   })
 
+  it("returns true when child status is missing but descendants are idle", async () => {
+    // given
+    spyOn(console, "log").mockImplementation(() => {})
+    const ctx = createMockContext({
+      childrenBySession: {
+        "test-session": [{ id: "child-1" }],
+        "child-1": [],
+      },
+      statuses: {},
+    })
+    const { checkCompletionConditions } = await import("./completion")
+
+    // when
+    const result = await checkCompletionConditions(ctx)
+
+    // then
+    expect(result).toBe(true)
+  })
+
+  it("returns false when descendant is busy even if parent status is missing", async () => {
+    // given
+    spyOn(console, "log").mockImplementation(() => {})
+    const ctx = createMockContext({
+      childrenBySession: {
+        "test-session": [{ id: "child-1" }],
+        "child-1": [{ id: "grandchild-1" }],
+        "grandchild-1": [],
+      },
+      statuses: {
+        "grandchild-1": { type: "busy" },
+      },
+    })
+    const { checkCompletionConditions } = await import("./completion")
+
+    // when
+    const result = await checkCompletionConditions(ctx)
+
+    // then
+    expect(result).toBe(false)
+  })
+
   it("returns true when all descendants idle (recursive)", async () => {
     // given
     spyOn(console, "log").mockImplementation(() => {})

src/cli/run/completion.ts

@@ -1,10 +1,22 @@
 import pc from "picocolors"
 import type { RunContext, Todo, ChildSession, SessionStatus } from "./types"
 import { normalizeSDKResponse } from "../../shared"
+import {
+  getContinuationState,
+  type ContinuationState,
+} from "./continuation-state"
 
 export async function checkCompletionConditions(ctx: RunContext): Promise<boolean> {
   try {
-    if (!await areAllTodosComplete(ctx)) {
+    const continuationState = getContinuationState(ctx.directory, ctx.sessionID)
+
+    if (continuationState.hasActiveHookMarker) {
+      const reason = continuationState.activeHookMarkerReason ?? "continuation hook is active"
+      console.log(pc.dim(`  Waiting: ${reason}`))
+      return false
+    }
+
+    if (!continuationState.hasTodoHookMarker && !await areAllTodosComplete(ctx)) {
       return false
     }
 
@@ -12,6 +24,10 @@ export async function checkCompletionConditions(ctx: RunContext): Promise<boolea
       return false
     }
 
+    if (!areContinuationHooksIdle(continuationState)) {
+      return false
+    }
+
     return true
   } catch (err) {
     console.error(pc.red(`[completion] API error: ${err}`))
@@ -19,6 +35,20 @@ export async function checkCompletionConditions(ctx: RunContext): Promise<boolea
   }
 }
 
+function areContinuationHooksIdle(continuationState: ContinuationState): boolean {
+  if (continuationState.hasActiveBoulder) {
+    console.log(pc.dim("  Waiting: boulder continuation is active"))
+    return false
+  }
+
+  if (continuationState.hasActiveRalphLoop) {
+    console.log(pc.dim("  Waiting: ralph-loop continuation is active"))
+    return false
+  }
+
+  return true
+}
+
 async function areAllTodosComplete(ctx: RunContext): Promise<boolean> {
   const todosRes = await ctx.client.session.todo({
     path: { id: ctx.sessionID },

src/cli/run/continuation-state-marker.test.ts

@@ -0,0 +1,54 @@
+import { afterEach, describe, expect, it } from "bun:test"
+import { mkdtempSync, rmSync } from "node:fs"
+import { join } from "node:path"
+import { tmpdir } from "node:os"
+import { setContinuationMarkerSource } from "../../features/run-continuation-state"
+import { getContinuationState } from "./continuation-state"
+
+const tempDirs: string[] = []
+
+function createTempDir(): string {
+  const directory = mkdtempSync(join(tmpdir(), "omo-run-cont-state-"))
+  tempDirs.push(directory)
+  return directory
+}
+
+afterEach(() => {
+  while (tempDirs.length > 0) {
+    const directory = tempDirs.pop()
+    if (directory) {
+      rmSync(directory, { recursive: true, force: true })
+    }
+  }
+})
+
+describe("getContinuationState marker integration", () => {
+  it("reports active marker state from continuation hooks", () => {
+    // given
+    const directory = createTempDir()
+    const sessionID = "ses_marker_active"
+    setContinuationMarkerSource(directory, sessionID, "todo", "active", "todos remaining")
+
+    // when
+    const state = getContinuationState(directory, sessionID)
+
+    // then
+    expect(state.hasActiveHookMarker).toBe(true)
+    expect(state.activeHookMarkerReason).toContain("todos")
+  })
+
+  it("does not report active marker when all sources are idle/stopped", () => {
+    // given
+    const directory = createTempDir()
+    const sessionID = "ses_marker_idle"
+    setContinuationMarkerSource(directory, sessionID, "todo", "idle")
+    setContinuationMarkerSource(directory, sessionID, "stop", "stopped")
+
+    // when
+    const state = getContinuationState(directory, sessionID)
+
+    // then
+    expect(state.hasActiveHookMarker).toBe(false)
+    expect(state.activeHookMarkerReason).toBeNull()
+  })
+})

src/cli/run/continuation-state.ts

@@ -0,0 +1,49 @@
+import { getPlanProgress, readBoulderState } from "../../features/boulder-state"
+import {
+  getActiveContinuationMarkerReason,
+  isContinuationMarkerActive,
+  readContinuationMarker,
+} from "../../features/run-continuation-state"
+import { readState as readRalphLoopState } from "../../hooks/ralph-loop/storage"
+
+export interface ContinuationState {
+  hasActiveBoulder: boolean
+  hasActiveRalphLoop: boolean
+  hasHookMarker: boolean
+  hasTodoHookMarker: boolean
+  hasActiveHookMarker: boolean
+  activeHookMarkerReason: string | null
+}
+
+export function getContinuationState(directory: string, sessionID: string): ContinuationState {
+  const marker = readContinuationMarker(directory, sessionID)
+
+  return {
+    hasActiveBoulder: hasActiveBoulderContinuation(directory, sessionID),
+    hasActiveRalphLoop: hasActiveRalphLoopContinuation(directory, sessionID),
+    hasHookMarker: marker !== null,
+    hasTodoHookMarker: marker?.sources.todo !== undefined,
+    hasActiveHookMarker: isContinuationMarkerActive(marker),
+    activeHookMarkerReason: getActiveContinuationMarkerReason(marker),
+  }
+}
+
+function hasActiveBoulderContinuation(directory: string, sessionID: string): boolean {
+  const boulder = readBoulderState(directory)
+  if (!boulder) return false
+  if (!boulder.session_ids.includes(sessionID)) return false
+
+  const progress = getPlanProgress(boulder.active_plan)
+  return !progress.isComplete
+}
+
+function hasActiveRalphLoopContinuation(directory: string, sessionID: string): boolean {
+  const state = readRalphLoopState(directory)
+  if (!state || !state.active) return false
+
+  if (state.session_id && state.session_id !== sessionID) {
+    return false
+  }
+
+  return true
+}

src/cli/run/display-chars.ts

@@ -0,0 +1,7 @@
+const isCI = Boolean(process.env.CI || process.env.GITHUB_ACTIONS)
+
+export const displayChars = {
+  treeEnd: isCI ? "`-" : "└─",
+  treeIndent: "   ",
+  treeJoin: isCI ? "   " : "      ",
+} as const

src/cli/run/event-formatting.ts

@@ -4,6 +4,7 @@ import type {
   EventPayload,
   MessageUpdatedProps,
   MessagePartUpdatedProps,
+  MessagePartDeltaProps,
   ToolExecuteProps,
   ToolResultProps,
   SessionErrorProps,
@@ -93,6 +94,15 @@ export function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
       break
     }
 
+    case "message.part.delta": {
+      const deltaProps = props as MessagePartDeltaProps | undefined
+      const field = deltaProps?.field ?? "unknown"
+      const delta = deltaProps?.delta ?? ""
+      const preview = delta.slice(0, 80).replace(/\n/g, "\\n")
+      console.error(pc.dim(`${sessionTag} message.part.delta (${field}): "${preview}${delta.length > 80 ? "..." : ""}"`))
+      break
+    }
+
     case "message.updated": {
       const msgProps = props as MessageUpdatedProps | undefined
       const role = msgProps?.info?.role ?? "unknown"

src/cli/run/event-handlers.ts

@@ -7,12 +7,21 @@ import type {
   SessionErrorProps,
   MessageUpdatedProps,
   MessagePartUpdatedProps,
+  MessagePartDeltaProps,
   ToolExecuteProps,
   ToolResultProps,
   TuiToastShowProps,
 } from "./types"
 import type { EventState } from "./event-state"
 import { serializeError } from "./event-formatting"
+import { formatToolHeader } from "./tool-input-preview"
+import { displayChars } from "./display-chars"
+import {
+  closeThinkBlock,
+  openThinkBlock,
+  renderAgentHeader,
+  writePaddedText,
+} from "./output-renderer"
 
 function getSessionId(props?: { sessionID?: string; sessionId?: string }): string | undefined {
   return props?.sessionID ?? props?.sessionId
@@ -30,6 +39,18 @@ function getPartSessionId(props?: {
   return props?.part?.sessionID ?? props?.part?.sessionId
 }
 
+function getPartMessageId(props?: {
+  part?: { messageID?: string }
+}): string | undefined {
+  return props?.part?.messageID
+}
+
+function getDeltaMessageId(props?: {
+  messageID?: string
+}): string | undefined {
+  return props?.messageID
+}
+
 export function handleSessionIdle(ctx: RunContext, payload: EventPayload, state: EventState): void {
   if (payload.type !== "session.idle") return
 
@@ -74,13 +95,41 @@ export function handleMessagePartUpdated(ctx: RunContext, payload: EventPayload,
   const infoSid = getInfoSessionId(props)
   if ((partSid ?? infoSid) !== ctx.sessionID) return
 
+  const role = props?.info?.role
+  const mappedRole = getPartMessageId(props)
+    ? state.messageRoleById[getPartMessageId(props) ?? ""]
+    : undefined
+  if ((role ?? mappedRole) === "user") return
+
   const part = props?.part
   if (!part) return
 
+  if (part.id && part.type) {
+    state.partTypesById[part.id] = part.type
+  }
+
+  if (part.type === "reasoning") {
+    ensureThinkBlockOpen(state)
+    const reasoningText = part.text ?? ""
+    const newText = reasoningText.slice(state.lastReasoningText.length)
+    if (newText) {
+      const padded = writePaddedText(newText, state.thinkingAtLineStart)
+      process.stdout.write(pc.dim(padded.output))
+      state.thinkingAtLineStart = padded.atLineStart
+      state.hasReceivedMeaningfulWork = true
+    }
+    state.lastReasoningText = reasoningText
+    return
+  }
+
+  closeThinkBlockIfNeeded(state)
+
   if (part.type === "text" && part.text) {
     const newText = part.text.slice(state.lastPartText.length)
     if (newText) {
-      process.stdout.write(newText)
+      const padded = writePaddedText(newText, state.textAtLineStart)
+      process.stdout.write(padded.output)
+      state.textAtLineStart = padded.atLineStart
       state.hasReceivedMeaningfulWork = true
     }
     state.lastPartText = part.text
@@ -91,6 +140,44 @@ export function handleMessagePartUpdated(ctx: RunContext, payload: EventPayload,
   }
 }
 
+export function handleMessagePartDelta(ctx: RunContext, payload: EventPayload, state: EventState): void {
+  if (payload.type !== "message.part.delta") return
+
+  const props = payload.properties as MessagePartDeltaProps | undefined
+  const sessionID = props?.sessionID ?? props?.sessionId
+  if (sessionID !== ctx.sessionID) return
+
+  const role = getDeltaMessageId(props)
+    ? state.messageRoleById[getDeltaMessageId(props) ?? ""]
+    : undefined
+  if (role === "user") return
+
+  if (props?.field !== "text") return
+
+  const partType = props?.partID ? state.partTypesById[props.partID] : undefined
+
+  const delta = props.delta ?? ""
+  if (!delta) return
+
+  if (partType === "reasoning") {
+    ensureThinkBlockOpen(state)
+    const padded = writePaddedText(delta, state.thinkingAtLineStart)
+    process.stdout.write(pc.dim(padded.output))
+    state.thinkingAtLineStart = padded.atLineStart
+    state.lastReasoningText += delta
+    state.hasReceivedMeaningfulWork = true
+    return
+  }
+
+  closeThinkBlockIfNeeded(state)
+
+  const padded = writePaddedText(delta, state.textAtLineStart)
+  process.stdout.write(padded.output)
+  state.textAtLineStart = padded.atLineStart
+  state.lastPartText += delta
+  state.hasReceivedMeaningfulWork = true
+}
+
 function handleToolPart(
   _ctx: RunContext,
   part: NonNullable<MessagePartUpdatedProps["part"]>,
@@ -100,34 +187,26 @@ function handleToolPart(
   const status = part.state?.status
 
   if (status === "running") {
+    if (state.currentTool !== null) return
     state.currentTool = toolName
-    let inputPreview = ""
-    const input = part.state?.input
-    if (input) {
-      if (input.command) {
-        inputPreview = ` ${pc.dim(String(input.command).slice(0, 60))}`
-      } else if (input.pattern) {
-        inputPreview = ` ${pc.dim(String(input.pattern).slice(0, 40))}`
-      } else if (input.filePath) {
-        inputPreview = ` ${pc.dim(String(input.filePath))}`
-      } else if (input.query) {
-        inputPreview = ` ${pc.dim(String(input.query).slice(0, 40))}`
-      }
-    }
+    const header = formatToolHeader(toolName, part.state?.input ?? {})
+    const suffix = header.description ? ` ${pc.dim(header.description)}` : ""
     state.hasReceivedMeaningfulWork = true
-    process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
+    process.stdout.write(`\n  ${pc.cyan(header.icon)} ${pc.bold(header.title)}${suffix}  \n`)
   }
 
   if (status === "completed" || status === "error") {
+    if (state.currentTool === null) return
     const output = part.state?.output || ""
-    const maxLen = 200
-    const preview = output.length > maxLen ? output.slice(0, maxLen) + "..." : output
-    if (preview.trim()) {
-      const lines = preview.split("\n").slice(0, 3)
-      process.stdout.write(pc.dim(`   └─ ${lines.join("\n      ")}\n`))
+    if (output.trim()) {
+      process.stdout.write(pc.dim(`  ${displayChars.treeEnd} output  \n`))
+      const padded = writePaddedText(output, true)
+      process.stdout.write(pc.dim(padded.output + (padded.atLineStart ? "" : "  ")))
+      process.stdout.write("\n")
     }
     state.currentTool = null
     state.lastPartText = ""
+    state.textAtLineStart = true
   }
 }
 
@@ -136,11 +215,40 @@ export function handleMessageUpdated(ctx: RunContext, payload: EventPayload, sta
 
   const props = payload.properties as MessageUpdatedProps | undefined
   if (getInfoSessionId(props) !== ctx.sessionID) return
+
+  state.currentMessageRole = props?.info?.role ?? null
+
+  const messageID = props?.info?.id ?? null
+  const role = props?.info?.role
+  if (messageID && role) {
+    state.messageRoleById[messageID] = role
+  }
+
   if (props?.info?.role !== "assistant") return
 
-  state.hasReceivedMeaningfulWork = true
-  state.messageCount++
-  state.lastPartText = ""
+  const isNewMessage = !messageID || messageID !== state.currentMessageId
+  if (isNewMessage) {
+    state.currentMessageId = messageID
+    state.hasReceivedMeaningfulWork = true
+    state.messageCount++
+    state.lastPartText = ""
+    state.lastReasoningText = ""
+    state.hasPrintedThinkingLine = false
+    state.lastThinkingSummary = ""
+    state.textAtLineStart = true
+    state.thinkingAtLineStart = false
+    closeThinkBlockIfNeeded(state)
+  }
+
+  const agent = props?.info?.agent ?? null
+  const model = props?.info?.modelID ?? null
+  const variant = props?.info?.variant ?? null
+  if (agent !== state.currentAgent || model !== state.currentModel || variant !== state.currentVariant) {
+    state.currentAgent = agent
+    state.currentModel = model
+    state.currentVariant = variant
+    renderAgentHeader(agent, model, variant, state.agentColorsByName)
+  }
 }
 
 export function handleToolExecute(ctx: RunContext, payload: EventPayload, state: EventState): void {
@@ -149,25 +257,17 @@ export function handleToolExecute(ctx: RunContext, payload: EventPayload, state:
   const props = payload.properties as ToolExecuteProps | undefined
   if (getSessionId(props) !== ctx.sessionID) return
 
+  closeThinkBlockIfNeeded(state)
+
+  if (state.currentTool !== null) return
+
   const toolName = props?.name || "unknown"
   state.currentTool = toolName
-
-  let inputPreview = ""
-  if (props?.input) {
-    const input = props.input
-    if (input.command) {
-      inputPreview = ` ${pc.dim(String(input.command).slice(0, 60))}`
-    } else if (input.pattern) {
-      inputPreview = ` ${pc.dim(String(input.pattern).slice(0, 40))}`
-    } else if (input.filePath) {
-      inputPreview = ` ${pc.dim(String(input.filePath))}`
-    } else if (input.query) {
-      inputPreview = ` ${pc.dim(String(input.query).slice(0, 40))}`
-    }
-  }
+  const header = formatToolHeader(toolName, props?.input ?? {})
+  const suffix = header.description ? ` ${pc.dim(header.description)}` : ""
 
   state.hasReceivedMeaningfulWork = true
-  process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
+  process.stdout.write(`\n  ${pc.cyan(header.icon)} ${pc.bold(header.title)}${suffix}  \n`)
 }
 
 export function handleToolResult(ctx: RunContext, payload: EventPayload, state: EventState): void {
@@ -176,36 +276,52 @@ export function handleToolResult(ctx: RunContext, payload: EventPayload, state:
   const props = payload.properties as ToolResultProps | undefined
   if (getSessionId(props) !== ctx.sessionID) return
 
-  const output = props?.output || ""
-  const maxLen = 200
-  const preview = output.length > maxLen ? output.slice(0, maxLen) + "..." : output
+  closeThinkBlockIfNeeded(state)
 
-  if (preview.trim()) {
-    const lines = preview.split("\n").slice(0, 3)
-    process.stdout.write(pc.dim(`   └─ ${lines.join("\n      ")}\n`))
+  if (state.currentTool === null) return
+
+  const output = props?.output || ""
+  if (output.trim()) {
+    process.stdout.write(pc.dim(`  ${displayChars.treeEnd} output  \n`))
+    const padded = writePaddedText(output, true)
+    process.stdout.write(pc.dim(padded.output + (padded.atLineStart ? "" : "  ")))
+    process.stdout.write("\n")
   }
 
   state.currentTool = null
   state.lastPartText = ""
+  state.textAtLineStart = true
 }
 
 export function handleTuiToast(_ctx: RunContext, payload: EventPayload, state: EventState): void {
   if (payload.type !== "tui.toast.show") return
 
   const props = payload.properties as TuiToastShowProps | undefined
-  const title = props?.title ? `${props.title}: ` : ""
-  const message = props?.message?.trim()
   const variant = props?.variant ?? "info"
 
-  if (!message) return
-
   if (variant === "error") {
-    state.mainSessionError = true
-    state.lastError = `${title}${message}`
-    console.error(pc.red(`\n[tui.toast.error] ${state.lastError}`))
-    return
+    const title = props?.title ? `${props.title}: ` : ""
+    const message = props?.message?.trim()
+    if (message) {
+      state.mainSessionError = true
+      state.lastError = `${title}${message}`
+    }
   }
-
-  const colorize = variant === "warning" ? pc.yellow : pc.dim
-  console.log(colorize(`[toast:${variant}] ${title}${message}`))
+}
+
+function ensureThinkBlockOpen(state: EventState): void {
+  if (state.inThinkBlock) return
+  openThinkBlock()
+  state.inThinkBlock = true
+  state.hasPrintedThinkingLine = false
+  state.thinkingAtLineStart = false
+}
+
+function closeThinkBlockIfNeeded(state: EventState): void {
+  if (!state.inThinkBlock) return
+  closeThinkBlock()
+  state.inThinkBlock = false
+  state.lastThinkingLineWidth = 0
+  state.lastThinkingSummary = ""
+  state.thinkingAtLineStart = false
 }

src/cli/run/event-state.ts

@@ -9,6 +9,36 @@ export interface EventState {
   hasReceivedMeaningfulWork: boolean
   /** Count of assistant messages for the main session */
   messageCount: number
+  /** Current agent name from the latest assistant message */
+  currentAgent: string | null
+  /** Current model ID from the latest assistant message */
+  currentModel: string | null
+  /** Current model variant from the latest assistant message */
+  currentVariant: string | null
+  /** Current message role (user/assistant) — used to filter user messages from display */
+  currentMessageRole: string | null
+  /** Agent profile colors keyed by display name */
+  agentColorsByName: Record<string, string>
+  /** Part type registry keyed by partID (text, reasoning, tool, ...) */
+  partTypesById: Record<string, string>
+  /** Whether a THINK block is currently open in output */
+  inThinkBlock: boolean
+  /** Tracks streamed reasoning text to avoid duplicates */
+  lastReasoningText: string
+  /** Whether compact thinking line already printed for current reasoning block */
+  hasPrintedThinkingLine: boolean
+  /** Last rendered thinking line width (for in-place padding updates) */
+  lastThinkingLineWidth: number
+  /** Message role lookup by message ID to filter user parts */
+  messageRoleById: Record<string, string>
+  /** Last rendered thinking summary (to avoid duplicate re-render) */
+  lastThinkingSummary: string
+  /** Whether text stream is currently at line start (for padding) */
+  textAtLineStart: boolean
+  /** Whether reasoning stream is currently at line start (for padding) */
+  thinkingAtLineStart: boolean
+  /** Current assistant message ID — prevents counter resets on repeated message.updated for same message */
+  currentMessageId: string | null
 }
 
 export function createEventState(): EventState {
@@ -21,5 +51,20 @@ export function createEventState(): EventState {
     currentTool: null,
     hasReceivedMeaningfulWork: false,
     messageCount: 0,
+    currentAgent: null,
+    currentModel: null,
+    currentVariant: null,
+    currentMessageRole: null,
+    agentColorsByName: {},
+    partTypesById: {},
+    inThinkBlock: false,
+    lastReasoningText: "",
+    hasPrintedThinkingLine: false,
+    lastThinkingLineWidth: 0,
+    messageRoleById: {},
+    lastThinkingSummary: "",
+    textAtLineStart: true,
+    thinkingAtLineStart: false,
+    currentMessageId: null,
   }
 }

src/cli/run/event-stream-processor.ts

@@ -7,6 +7,7 @@ import {
   handleSessionIdle,
   handleSessionStatus,
   handleMessagePartUpdated,
+  handleMessagePartDelta,
   handleMessageUpdated,
   handleToolExecute,
   handleToolResult,
@@ -24,16 +25,21 @@ export async function processEvents(
     try {
       const payload = event as EventPayload
       if (!payload?.type) {
-        console.error(pc.dim(`[event] no type: ${JSON.stringify(event)}`))
+        if (ctx.verbose) {
+          console.error(pc.dim(`[event] no type: ${JSON.stringify(event)}`))
+        }
         continue
       }
 
-      logEventVerbose(ctx, payload)
+      if (ctx.verbose) {
+        logEventVerbose(ctx, payload)
+      }
 
       handleSessionError(ctx, payload, state)
       handleSessionIdle(ctx, payload, state)
       handleSessionStatus(ctx, payload, state)
       handleMessagePartUpdated(ctx, payload, state)
+      handleMessagePartDelta(ctx, payload, state)
       handleMessageUpdated(ctx, payload, state)
       handleToolExecute(ctx, payload, state)
       handleToolResult(ctx, payload, state)

src/cli/run/events.test.ts

@@ -1,4 +1,4 @@
-import { describe, it, expect } from "bun:test"
+import { describe, it, expect, spyOn } from "bun:test"
 import { createEventState, serializeError, type EventState } from "./events"
 import type { RunContext, EventPayload } from "./types"
 
@@ -87,6 +87,52 @@ describe("createEventState", () => {
 })
 
 describe("event handling", () => {
+  it("does not log verbose event traces by default", async () => {
+    // given
+    const ctx = createMockContext("my-session")
+    const state = createEventState()
+    const errorSpy = spyOn(console, "error").mockImplementation(() => {})
+
+    const payload: EventPayload = {
+      type: "custom.event",
+      properties: { sessionID: "my-session" },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // when
+    await processEvents(ctx, events, state)
+
+    // then
+    expect(errorSpy).not.toHaveBeenCalled()
+    errorSpy.mockRestore()
+  })
+
+  it("logs full event traces when verbose is enabled", async () => {
+    // given
+    const ctx = { ...createMockContext("my-session"), verbose: true }
+    const state = createEventState()
+    const errorSpy = spyOn(console, "error").mockImplementation(() => {})
+
+    const payload: EventPayload = {
+      type: "custom.event",
+      properties: { sessionID: "my-session" },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // when
+    await processEvents(ctx, events, state)
+
+    // then
+    expect(errorSpy).toHaveBeenCalledTimes(1)
+    const firstCall = errorSpy.mock.calls[0]
+    expect(String(firstCall?.[0] ?? "")).toContain("custom.event")
+    errorSpy.mockRestore()
+  })
+
   it("session.idle sets mainSessionIdle to true for matching session", async () => {
     // given
     const ctx = createMockContext("my-session")

src/cli/run/message-part-delta.test.ts

@@ -0,0 +1,657 @@
+import { describe, expect, it, spyOn } from "bun:test"
+import type { EventPayload, RunContext } from "./types"
+import { createEventState } from "./events"
+import { processEvents } from "./event-stream-processor"
+
+function stripAnsi(str: string): string {
+  return str.replace(new RegExp("\x1b\\[[0-9;]*m", "g"), "")
+}
+
+const createMockContext = (sessionID: string = "test-session"): RunContext => ({
+  client: {} as RunContext["client"],
+  sessionID,
+  directory: "/test",
+  abortController: new AbortController(),
+})
+
+async function* toAsyncIterable<T>(items: T[]): AsyncIterable<T> {
+  for (const item of items) {
+    yield item
+  }
+}
+
+describe("message.part.delta handling", () => {
+  it("prints streaming text incrementally from delta events", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          field: "text",
+          delta: "Hello",
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          field: "text",
+          delta: " world",
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    expect(state.hasReceivedMeaningfulWork).toBe(true)
+    expect(state.lastPartText).toBe("Hello world")
+    expect(stdoutSpy).toHaveBeenCalledTimes(2)
+    stdoutSpy.mockRestore()
+  })
+
+  it("does not suppress assistant tool/text parts when state role is stale user", () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    state.currentMessageRole = "user"
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const payload: EventPayload = {
+      type: "message.part.updated",
+      properties: {
+        part: {
+          sessionID: "ses_main",
+          type: "tool",
+          tool: "task_create",
+          state: { status: "running" },
+        },
+      },
+    }
+
+    //#when
+    const { handleMessagePartUpdated } = require("./event-handlers") as {
+      handleMessagePartUpdated: (ctx: RunContext, payload: EventPayload, state: ReturnType<typeof createEventState>) => void
+    }
+    handleMessagePartUpdated(ctx, payload, state)
+
+    //#then
+    expect(state.currentTool).toBe("task_create")
+    expect(state.hasReceivedMeaningfulWork).toBe(true)
+    stdoutSpy.mockRestore()
+  })
+
+  it("renders agent header using profile hex color when available", () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    state.agentColorsByName["Sisyphus (Ultraworker)"] = "#00CED1"
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const payload: EventPayload = {
+      type: "message.updated",
+      properties: {
+        info: {
+          sessionID: "ses_main",
+          role: "assistant",
+          agent: "Sisyphus (Ultraworker)",
+          modelID: "claude-opus-4-6",
+          variant: "max",
+        },
+      },
+    }
+
+    //#when
+    const { handleMessageUpdated } = require("./event-handlers") as {
+      handleMessageUpdated: (ctx: RunContext, payload: EventPayload, state: ReturnType<typeof createEventState>) => void
+    }
+    handleMessageUpdated(ctx, payload, state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    expect(rendered).toContain("\u001b[38;2;0;206;209m")
+    expect(rendered).toContain("claude-opus-4-6 (max)")
+    expect(rendered).toContain("└─")
+    expect(rendered).toContain("Sisyphus (Ultraworker)")
+    stdoutSpy.mockRestore()
+  })
+
+  it("separates think block output from normal response output", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { sessionID: "ses_main", role: "assistant", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "think-1", sessionID: "ses_main", type: "reasoning", text: "" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          partID: "think-1",
+          field: "text",
+          delta: "Composing final summary in Korean with clear concise structure",
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "text-1", sessionID: "ses_main", type: "text", text: "" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          partID: "text-1",
+          field: "text",
+          delta: "answer",
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const plain = stripAnsi(rendered)
+    expect(plain).toContain("Thinking:")
+    expect(plain).toContain("Composing final summary in Korean")
+    expect(plain).toContain("answer")
+    stdoutSpy.mockRestore()
+  })
+
+  it("updates thinking line incrementally on delta updates", async () => {
+    //#given
+    const previous = process.env.GITHUB_ACTIONS
+    delete process.env.GITHUB_ACTIONS
+
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { sessionID: "ses_main", role: "assistant", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "think-1", sessionID: "ses_main", type: "reasoning", text: "" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          partID: "think-1",
+          field: "text",
+          delta: "Composing final summary",
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          partID: "think-1",
+          field: "text",
+          delta: " in Korean with specifics.",
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const plain = stripAnsi(rendered)
+    expect(plain).toContain("Thinking:")
+    expect(plain).toContain("Composing final summary")
+    expect(plain).toContain("in Korean with specifics.")
+
+    if (previous !== undefined) process.env.GITHUB_ACTIONS = previous
+    stdoutSpy.mockRestore()
+  })
+
+  it("does not re-render identical thinking summary repeatedly", async () => {
+    //#given
+    const previous = process.env.GITHUB_ACTIONS
+    delete process.env.GITHUB_ACTIONS
+
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_assistant", sessionID: "ses_main", role: "assistant", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "think-1", messageID: "msg_assistant", sessionID: "ses_main", type: "reasoning", text: "" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_assistant",
+          partID: "think-1",
+          field: "text",
+          delta: "The user wants me",
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_assistant",
+          partID: "think-1",
+          field: "text",
+          delta: " to",
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_assistant",
+          partID: "think-1",
+          field: "text",
+          delta: " ",
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const plain = stripAnsi(rendered)
+    const renderCount = plain.split("Thinking:").length - 1
+    expect(renderCount).toBe(1)
+
+    if (previous !== undefined) process.env.GITHUB_ACTIONS = previous
+    stdoutSpy.mockRestore()
+  })
+
+  it("does not truncate thinking content", async () => {
+    //#given
+    const previous = process.env.GITHUB_ACTIONS
+    delete process.env.GITHUB_ACTIONS
+
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const longThinking = "This is a very long thinking stream that should never be truncated and must include final tail marker END-OF-THINKING-MARKER"
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_assistant", sessionID: "ses_main", role: "assistant", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "think-1", messageID: "msg_assistant", sessionID: "ses_main", type: "reasoning", text: "" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_assistant",
+          partID: "think-1",
+          field: "text",
+          delta: longThinking,
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    expect(rendered).toContain("END-OF-THINKING-MARKER")
+
+    if (previous !== undefined) process.env.GITHUB_ACTIONS = previous
+    stdoutSpy.mockRestore()
+  })
+
+  it("applies left and right padding to assistant text output", async () => {
+    //#given
+    const previous = process.env.GITHUB_ACTIONS
+    delete process.env.GITHUB_ACTIONS
+
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_assistant", sessionID: "ses_main", role: "assistant", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6", variant: "max" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_assistant",
+          partID: "part_assistant_text",
+          field: "text",
+          delta: "hello\nworld",
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    expect(rendered).toContain("  hello  \n  world")
+
+    if (previous !== undefined) process.env.GITHUB_ACTIONS = previous
+    stdoutSpy.mockRestore()
+  })
+
+  it("does not render user message parts in output stream", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_user", sessionID: "ses_main", role: "user", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "part_user_text", messageID: "msg_user", sessionID: "ses_main", type: "text", text: "[search-mode] should not print" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_user",
+          partID: "part_user_text",
+          field: "text",
+          delta: "still should not print",
+        },
+      },
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_assistant", sessionID: "ses_main", role: "assistant", agent: "Sisyphus (Ultraworker)", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_assistant",
+          partID: "part_assistant_text",
+          field: "text",
+          delta: "assistant output",
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    expect(rendered.includes("[search-mode] should not print")).toBe(false)
+    expect(rendered.includes("still should not print")).toBe(false)
+    expect(rendered).toContain("assistant output")
+    stdoutSpy.mockRestore()
+  })
+
+  it("renders tool header and full tool output without truncation", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const longTail = "END-OF-TOOL-OUTPUT-MARKER"
+    const events: EventPayload[] = [
+      {
+        type: "tool.execute",
+        properties: {
+          sessionID: "ses_main",
+          name: "read",
+          input: { filePath: "src/index.ts", offset: 1, limit: 200 },
+        },
+      },
+      {
+        type: "tool.result",
+        properties: {
+          sessionID: "ses_main",
+          name: "read",
+          output: `line1\nline2\n${longTail}`,
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    expect(rendered).toContain("→")
+    expect(rendered).toContain("Read src/index.ts")
+    expect(rendered).toContain("END-OF-TOOL-OUTPUT-MARKER")
+    stdoutSpy.mockRestore()
+  })
+
+  it("renders tool header only once when message.part.updated fires multiple times for same running tool", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.part.updated",
+        properties: {
+          part: {
+            id: "tool-1",
+            sessionID: "ses_main",
+            type: "tool",
+            tool: "bash",
+            state: { status: "running", input: { command: "bun test" } },
+          },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: {
+            id: "tool-1",
+            sessionID: "ses_main",
+            type: "tool",
+            tool: "bash",
+            state: { status: "running", input: { command: "bun test" } },
+          },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: {
+            id: "tool-1",
+            sessionID: "ses_main",
+            type: "tool",
+            tool: "bash",
+            state: { status: "running", input: { command: "bun test" } },
+          },
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const headerCount = rendered.split("bun test").length - 1
+    expect(headerCount).toBe(1)
+    stdoutSpy.mockRestore()
+  })
+
+  it("renders tool header only once when both tool.execute and message.part.updated fire", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "tool.execute",
+        properties: {
+          sessionID: "ses_main",
+          name: "bash",
+          input: { command: "bun test" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: {
+            id: "tool-1",
+            sessionID: "ses_main",
+            type: "tool",
+            tool: "bash",
+            state: { status: "running", input: { command: "bun test" } },
+          },
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const headerCount = rendered.split("bun test").length - 1
+    expect(headerCount).toBe(1)
+    stdoutSpy.mockRestore()
+  })
+
+  it("renders tool output only once when both tool.result and message.part.updated(completed) fire", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "tool.execute",
+        properties: {
+          sessionID: "ses_main",
+          name: "bash",
+          input: { command: "bun test" },
+        },
+      },
+      {
+        type: "tool.result",
+        properties: {
+          sessionID: "ses_main",
+          name: "bash",
+          output: "UNIQUE-OUTPUT-MARKER",
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: {
+            id: "tool-1",
+            sessionID: "ses_main",
+            type: "tool",
+            tool: "bash",
+            state: { status: "completed", input: { command: "bun test" }, output: "UNIQUE-OUTPUT-MARKER" },
+          },
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const outputCount = rendered.split("UNIQUE-OUTPUT-MARKER").length - 1
+    expect(outputCount).toBe(1)
+    stdoutSpy.mockRestore()
+  })
+
+  it("does not re-render text when message.updated fires multiple times for same message", async () => {
+    //#given
+    const ctx = createMockContext("ses_main")
+    const state = createEventState()
+    const stdoutSpy = spyOn(process.stdout, "write").mockImplementation(() => true)
+    const events: EventPayload[] = [
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_1", sessionID: "ses_main", role: "assistant", agent: "Sisyphus", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.delta",
+        properties: {
+          sessionID: "ses_main",
+          messageID: "msg_1",
+          field: "text",
+          delta: "Hello world",
+        },
+      },
+      {
+        type: "message.updated",
+        properties: {
+          info: { id: "msg_1", sessionID: "ses_main", role: "assistant", agent: "Sisyphus", modelID: "claude-opus-4-6" },
+        },
+      },
+      {
+        type: "message.part.updated",
+        properties: {
+          part: { id: "text-1", sessionID: "ses_main", type: "text", text: "Hello world" },
+        },
+      },
+    ]
+
+    //#when
+    await processEvents(ctx, toAsyncIterable(events), state)
+
+    //#then
+    const rendered = stdoutSpy.mock.calls.map((call) => String(call[0] ?? "")).join("")
+    const textCount = rendered.split("Hello world").length - 1
+    expect(textCount).toBe(1)
+    stdoutSpy.mockRestore()
+  })
+})

src/cli/run/output-renderer.ts

@@ -0,0 +1,90 @@
+import pc from "picocolors"
+
+export function renderAgentHeader(
+  agent: string | null,
+  model: string | null,
+  variant: string | null,
+  agentColorsByName: Record<string, string>,
+): void {
+  if (!agent && !model) return
+
+  const agentLabel = agent
+    ? pc.bold(colorizeWithProfileColor(agent, agentColorsByName[agent]))
+    : ""
+  const modelBase = model ?? ""
+  const variantSuffix = variant ? ` (${variant})` : ""
+  const modelLabel = model ? pc.dim(`${modelBase}${variantSuffix}`) : ""
+
+  process.stdout.write("\n")
+
+  if (modelLabel) {
+    process.stdout.write(`  ${modelLabel}  \n`)
+  }
+
+  if (agentLabel) {
+    process.stdout.write(`  ${pc.dim("└─")} ${agentLabel}  \n`)
+  }
+
+  process.stdout.write("\n")
+}
+
+export function openThinkBlock(): void {
+  process.stdout.write(`\n  ${pc.dim("┃  Thinking:")} `)
+}
+
+export function closeThinkBlock(): void {
+  process.stdout.write("  \n\n")
+}
+
+export function writePaddedText(
+  text: string,
+  atLineStart: boolean,
+): { output: string; atLineStart: boolean } {
+  const isGitHubActions = process.env.GITHUB_ACTIONS === "true"
+  if (isGitHubActions) {
+    return { output: text, atLineStart: text.endsWith("\n") }
+  }
+
+  let output = ""
+  let lineStart = atLineStart
+
+  for (let i = 0; i < text.length; i++) {
+    const ch = text[i]
+    if (lineStart) {
+      output += "  "
+      lineStart = false
+    }
+
+    if (ch === "\n") {
+      output += "  \n"
+      lineStart = true
+      continue
+    }
+
+    output += ch
+  }
+
+  return { output, atLineStart: lineStart }
+}
+
+function colorizeWithProfileColor(text: string, hexColor?: string): string {
+  if (!hexColor) return pc.magenta(text)
+
+  const rgb = parseHexColor(hexColor)
+  if (!rgb) return pc.magenta(text)
+
+  const [r, g, b] = rgb
+  return `\u001b[38;2;${r};${g};${b}m${text}\u001b[39m`
+}
+
+function parseHexColor(hexColor: string): [number, number, number] | null {
+  const cleaned = hexColor.trim()
+  const match = cleaned.match(/^#?([A-Fa-f0-9]{6})$/)
+  if (!match) return null
+
+  const hex = match[1]
+  const r = Number.parseInt(hex.slice(0, 2), 16)
+  const g = Number.parseInt(hex.slice(2, 4), 16)
+  const b = Number.parseInt(hex.slice(4, 6), 16)
+  return [r, g, b]
+}

src/cli/run/poll-for-completion.test.ts

@@ -94,6 +94,7 @@ describe("pollForCompletion", () => {
     const result = await pollForCompletion(ctx, eventState, abortController, {
       pollIntervalMs: 10,
       requiredConsecutive: 3,
+      minStabilizationMs: 500,
     })
 
     //#then - should be aborted, not completed (tool blocked exit)
@@ -159,6 +160,7 @@ describe("pollForCompletion", () => {
     const result = await pollForCompletion(ctx, eventState, abortController, {
       pollIntervalMs: 10,
       requiredConsecutive: 3,
+      minStabilizationMs: 500,
     })
 
     //#then
@@ -310,7 +312,7 @@ describe("pollForCompletion", () => {
     //#then - returns 1 (not 130/timeout), error message printed
     expect(result).toBe(1)
     const errorCalls = (console.error as ReturnType<typeof mock>).mock.calls
-    expect(errorCalls.some((call) => call[0]?.includes("Session ended with error"))).toBe(true)
+    expect(errorCalls.some((call: unknown[]) => String(call[0] ?? "").includes("Session ended with error"))).toBe(true)
   })
 
   it("returns 1 when session errors while tool is active (error not masked by tool gate)", async () => {
@@ -335,4 +337,5 @@ describe("pollForCompletion", () => {
     //#then - returns 1
     expect(result).toBe(1)
   })
+
 })

src/cli/run/poll-for-completion.ts

@@ -5,9 +5,9 @@ import { checkCompletionConditions } from "./completion"
 import { normalizeSDKResponse } from "../../shared"
 
 const DEFAULT_POLL_INTERVAL_MS = 500
-const DEFAULT_REQUIRED_CONSECUTIVE = 3
+const DEFAULT_REQUIRED_CONSECUTIVE = 1
 const ERROR_GRACE_CYCLES = 3
-const MIN_STABILIZATION_MS = 10_000
+const MIN_STABILIZATION_MS = 0
 
 export interface PollOptions {
   pollIntervalMs?: number
@@ -34,6 +34,10 @@ export async function pollForCompletion(
   while (!abortController.signal.aborted) {
     await new Promise((resolve) => setTimeout(resolve, pollIntervalMs))
 
+    if (abortController.signal.aborted) {
+      return 130
+    }
+
     // ERROR CHECK FIRST — errors must not be masked by other gates
     if (eventState.mainSessionError) {
       errorCycleCount++
@@ -71,6 +75,11 @@ export async function pollForCompletion(
     }
 
     if (!eventState.hasReceivedMeaningfulWork) {
+      if (minStabilizationMs <= 0) {
+        consecutiveCompleteChecks = 0
+        continue
+      }
+
       if (Date.now() - pollStartTimestamp < minStabilizationMs) {
         consecutiveCompleteChecks = 0
         continue
@@ -91,6 +100,10 @@ export async function pollForCompletion(
 
     const shouldExit = await checkCompletionConditions(ctx)
     if (shouldExit) {
+      if (abortController.signal.aborted) {
+        return 130
+      }
+
       consecutiveCompleteChecks++
       if (consecutiveCompleteChecks >= requiredConsecutive) {
         console.log(pc.green("\n\nAll tasks completed."))

src/cli/run/runner.test.ts

@@ -1,6 +1,6 @@
 /// <reference types="bun-types" />
 
-import { describe, it, expect, spyOn, afterEach } from "bun:test"
+import { describe, it, expect } from "bun:test"
 import type { OhMyOpenCodeConfig } from "../../config"
 import { resolveRunAgent, waitForEventProcessorShutdown } from "./runner"
 
@@ -83,14 +83,6 @@ describe("resolveRunAgent", () => {
 })
 
 describe("waitForEventProcessorShutdown", () => {
-  let consoleLogSpy: ReturnType<typeof spyOn<typeof console, "log">> | null = null
-
-  afterEach(() => {
-    if (consoleLogSpy) {
-      consoleLogSpy.mockRestore()
-      consoleLogSpy = null
-    }
-  })
 
   it("returns quickly when event processor completes", async () => {
     //#given
@@ -99,7 +91,6 @@ describe("waitForEventProcessorShutdown", () => {
         resolve()
       }, 25)
     })
-    consoleLogSpy = spyOn(console, "log").mockImplementation(() => {})
     const start = performance.now()
 
     //#when
@@ -108,29 +99,19 @@ describe("waitForEventProcessorShutdown", () => {
     //#then
     const elapsed = performance.now() - start
     expect(elapsed).toBeLessThan(200)
-    expect(console.log).not.toHaveBeenCalledWith(
-      "[run] Event stream did not close within 200ms after abort; continuing shutdown.",
-    )
   })
 
   it("times out and continues when event processor does not complete", async () => {
     //#given
     const eventProcessor = new Promise<void>(() => {})
-    const spy = spyOn(console, "log").mockImplementation(() => {})
-    consoleLogSpy = spy
     const timeoutMs = 200
     const start = performance.now()
 
-    try {
-      //#when
-      await waitForEventProcessorShutdown(eventProcessor, timeoutMs)
+    //#when
+    await waitForEventProcessorShutdown(eventProcessor, timeoutMs)
 
-      //#then
-      const elapsed = performance.now() - start
-      expect(elapsed).toBeGreaterThanOrEqual(timeoutMs - 10)
-      expect(spy.mock.calls.length).toBeGreaterThanOrEqual(1)
-    } finally {
-      spy.mockRestore()
-    }
+    //#then
+    const elapsed = performance.now() - start
+    expect(elapsed).toBeGreaterThanOrEqual(timeoutMs - 10)
   })
 })

src/cli/run/runner.ts

@@ -8,10 +8,10 @@ import { createJsonOutputManager } from "./json-output"
 import { executeOnCompleteHook } from "./on-complete-hook"
 import { resolveRunAgent } from "./agent-resolver"
 import { pollForCompletion } from "./poll-for-completion"
+import { loadAgentProfileColors } from "./agent-profile-colors"
 
 export { resolveRunAgent }
 
-const DEFAULT_TIMEOUT_MS = 600_000
 const EVENT_PROCESSOR_SHUTDOWN_TIMEOUT_MS = 2_000
 
 export async function waitForEventProcessorShutdown(
@@ -23,13 +23,7 @@ export async function waitForEventProcessorShutdown(
     new Promise<boolean>((resolve) => setTimeout(() => resolve(false), timeoutMs)),
   ])
 
-  if (!completed) {
-    console.log(
-      pc.dim(
-        `[run] Event stream did not close within ${timeoutMs}ms after abort; continuing shutdown.`,
-      ),
-    )
-  }
+  void completed
 }
 
 export async function run(options: RunOptions): Promise<number> {
@@ -39,7 +33,6 @@ export async function run(options: RunOptions): Promise<number> {
   const {
     message,
     directory = process.cwd(),
-    timeout = DEFAULT_TIMEOUT_MS,
   } = options
 
   const jsonManager = options.json ? createJsonOutputManager() : null
@@ -48,14 +41,6 @@ export async function run(options: RunOptions): Promise<number> {
   const pluginConfig = loadPluginConfig(directory, { command: "run" })
   const resolvedAgent = resolveRunAgent(options, pluginConfig)
   const abortController = new AbortController()
-  let timeoutId: ReturnType<typeof setTimeout> | null = null
-
-  if (timeout > 0) {
-    timeoutId = setTimeout(() => {
-      console.log(pc.yellow("\nTimeout reached. Aborting..."))
-      abortController.abort()
-    }, timeout)
-  }
 
   try {
     const { client, cleanup: serverCleanup } = await createServerConnection({
@@ -65,7 +50,6 @@ export async function run(options: RunOptions): Promise<number> {
     })
 
     const cleanup = () => {
-      if (timeoutId) clearTimeout(timeoutId)
       serverCleanup()
     }
 
@@ -84,14 +68,20 @@ export async function run(options: RunOptions): Promise<number> {
 
       console.log(pc.dim(`Session: ${sessionID}`))
 
-      const ctx: RunContext = { client, sessionID, directory, abortController }
+      const ctx: RunContext = {
+        client,
+        sessionID,
+        directory,
+        abortController,
+        verbose: options.verbose ?? false,
+      }
       const events = await client.event.subscribe({ query: { directory } })
       const eventState = createEventState()
+      eventState.agentColorsByName = await loadAgentProfileColors(client)
       const eventProcessor = processEvents(ctx, events.stream, eventState).catch(
         () => {},
       )
 
-      console.log(pc.dim("\nSending prompt..."))
       await client.session.promptAsync({
         path: { id: sessionID },
         body: {
@@ -100,8 +90,6 @@ export async function run(options: RunOptions): Promise<number> {
         },
         query: { directory },
       })
-
-      console.log(pc.dim("Waiting for completion...\n"))
       const exitCode = await pollForCompletion(ctx, eventState, abortController)
 
       // Abort the event stream to stop the processor
@@ -138,7 +126,6 @@ export async function run(options: RunOptions): Promise<number> {
       throw err
     }
   } catch (err) {
-    if (timeoutId) clearTimeout(timeoutId)
     if (jsonManager) jsonManager.restore()
     if (err instanceof Error && err.name === "AbortError") {
       return 130

src/cli/run/server-connection.test.ts

@@ -95,6 +95,24 @@ describe("createServerConnection", () => {
     expect(mockServerClose).toHaveBeenCalled()
   })
 
+  it("explicit port attaches when start fails because port became occupied", async () => {
+    // given
+    const signal = new AbortController().signal
+    const port = 8080
+    mockIsPortAvailable.mockResolvedValueOnce(true).mockResolvedValueOnce(false)
+    mockCreateOpencode.mockRejectedValueOnce(new Error("Failed to start server on port 8080"))
+
+    // when
+    const result = await createServerConnection({ port, signal })
+
+    // then
+    expect(mockIsPortAvailable).toHaveBeenNthCalledWith(1, 8080, "127.0.0.1")
+    expect(mockIsPortAvailable).toHaveBeenNthCalledWith(2, 8080, "127.0.0.1")
+    expect(mockCreateOpencodeClient).toHaveBeenCalledWith({ baseUrl: "http://127.0.0.1:8080" })
+    result.cleanup()
+    expect(mockServerClose).not.toHaveBeenCalled()
+  })
+
   it("explicit port attaches when port is occupied", async () => {
     // given
     const signal = new AbortController().signal
@@ -133,6 +151,32 @@ describe("createServerConnection", () => {
     expect(mockServerClose).toHaveBeenCalled()
   })
 
+  it("auto mode retries on next port when initial start fails", async () => {
+    // given
+    const signal = new AbortController().signal
+    mockGetAvailableServerPort
+      .mockResolvedValueOnce({ port: 4096, wasAutoSelected: false })
+      .mockResolvedValueOnce({ port: 4097, wasAutoSelected: true })
+
+    mockCreateOpencode
+      .mockRejectedValueOnce(new Error("Failed to start server on port 4096"))
+      .mockResolvedValueOnce({
+        client: { session: {} },
+        server: { url: "http://127.0.0.1:4097", close: mockServerClose },
+      })
+
+    // when
+    const result = await createServerConnection({ signal })
+
+    // then
+    expect(mockGetAvailableServerPort).toHaveBeenNthCalledWith(1, 4096, "127.0.0.1")
+    expect(mockGetAvailableServerPort).toHaveBeenNthCalledWith(2, 4097, "127.0.0.1")
+    expect(mockCreateOpencode).toHaveBeenNthCalledWith(1, { signal, port: 4096, hostname: "127.0.0.1" })
+    expect(mockCreateOpencode).toHaveBeenNthCalledWith(2, { signal, port: 4097, hostname: "127.0.0.1" })
+    result.cleanup()
+    expect(mockServerClose).toHaveBeenCalledTimes(1)
+  })
+
   it("invalid port throws error", async () => {
     // given
     const signal = new AbortController().signal

src/cli/run/server-connection.ts

@@ -5,6 +5,24 @@ import { getAvailableServerPort, isPortAvailable, DEFAULT_SERVER_PORT } from "..
 import { withWorkingOpencodePath } from "./opencode-binary-resolver"
 import { prependResolvedOpencodeBinToPath } from "./opencode-bin-path"
 
+function isPortStartFailure(error: unknown, port: number): boolean {
+  if (!(error instanceof Error)) {
+    return false
+  }
+
+  return error.message.includes(`Failed to start server on port ${port}`)
+}
+
+async function startServer(options: { signal: AbortSignal, port: number }): Promise<ServerConnection> {
+  const { signal, port } = options
+  const { client, server } = await withWorkingOpencodePath(() =>
+    createOpencode({ signal, port, hostname: "127.0.0.1" }),
+  )
+
+  console.log(pc.dim("Server listening at"), pc.cyan(server.url))
+  return { client, cleanup: () => server.close() }
+}
+
 export async function createServerConnection(options: {
   port?: number
   attach?: string
@@ -29,11 +47,22 @@ export async function createServerConnection(options: {
 
     if (available) {
       console.log(pc.dim("Starting server on port"), pc.cyan(port.toString()))
-      const { client, server } = await withWorkingOpencodePath(() =>
-        createOpencode({ signal, port, hostname: "127.0.0.1" }),
-      )
-      console.log(pc.dim("Server listening at"), pc.cyan(server.url))
-      return { client, cleanup: () => server.close() }
+      try {
+        return await startServer({ signal, port })
+      } catch (error) {
+        if (!isPortStartFailure(error, port)) {
+          throw error
+        }
+
+        const stillAvailable = await isPortAvailable(port, "127.0.0.1")
+        if (stillAvailable) {
+          throw error
+        }
+
+        console.log(pc.dim("Port"), pc.cyan(port.toString()), pc.dim("became occupied, attaching to existing server"))
+        const client = createOpencodeClient({ baseUrl: `http://127.0.0.1:${port}` })
+        return { client, cleanup: () => {} }
+      }
     }
 
     console.log(pc.dim("Port"), pc.cyan(port.toString()), pc.dim("is occupied, attaching to existing server"))
@@ -47,9 +76,16 @@ export async function createServerConnection(options: {
   } else {
     console.log(pc.dim("Starting server on port"), pc.cyan(selectedPort.toString()))
   }
-  const { client, server } = await withWorkingOpencodePath(() =>
-    createOpencode({ signal, port: selectedPort, hostname: "127.0.0.1" }),
-  )
-  console.log(pc.dim("Server listening at"), pc.cyan(server.url))
-  return { client, cleanup: () => server.close() }
+
+  try {
+    return await startServer({ signal, port: selectedPort })
+  } catch (error) {
+    if (!isPortStartFailure(error, selectedPort)) {
+      throw error
+    }
+
+    const { port: retryPort } = await getAvailableServerPort(selectedPort + 1, "127.0.0.1")
+    console.log(pc.dim("Retrying server start on port"), pc.cyan(retryPort.toString()))
+    return await startServer({ signal, port: retryPort })
+  }
 }

src/cli/run/tool-input-preview.ts

@@ -0,0 +1,144 @@
+export interface ToolHeader {
+  icon: string
+  title: string
+  description?: string
+}
+
+export function formatToolHeader(toolName: string, input: Record<string, unknown>): ToolHeader {
+  if (toolName === "glob") {
+    const pattern = str(input.pattern)
+    const root = str(input.path)
+    return {
+      icon: "✱",
+      title: pattern ? `Glob "${pattern}"` : "Glob",
+      description: root ? `in ${root}` : undefined,
+    }
+  }
+
+  if (toolName === "grep") {
+    const pattern = str(input.pattern)
+    const root = str(input.path)
+    return {
+      icon: "✱",
+      title: pattern ? `Grep "${pattern}"` : "Grep",
+      description: root ? `in ${root}` : undefined,
+    }
+  }
+
+  if (toolName === "list") {
+    const path = str(input.path)
+    return {
+      icon: "→",
+      title: path ? `List ${path}` : "List",
+    }
+  }
+
+  if (toolName === "read") {
+    const filePath = str(input.filePath)
+    return {
+      icon: "→",
+      title: filePath ? `Read ${filePath}` : "Read",
+      description: formatKeyValues(input, ["filePath"]),
+    }
+  }
+
+  if (toolName === "write") {
+    const filePath = str(input.filePath)
+    return {
+      icon: "←",
+      title: filePath ? `Write ${filePath}` : "Write",
+    }
+  }
+
+  if (toolName === "edit") {
+    const filePath = str(input.filePath)
+    return {
+      icon: "←",
+      title: filePath ? `Edit ${filePath}` : "Edit",
+      description: formatKeyValues(input, ["filePath", "oldString", "newString"]),
+    }
+  }
+
+  if (toolName === "webfetch") {
+    const url = str(input.url)
+    return {
+      icon: "%",
+      title: url ? `WebFetch ${url}` : "WebFetch",
+      description: formatKeyValues(input, ["url"]),
+    }
+  }
+
+  if (toolName === "websearch_web_search_exa") {
+    const query = str(input.query)
+    return {
+      icon: "◈",
+      title: query ? `Web Search "${query}"` : "Web Search",
+    }
+  }
+
+  if (toolName === "grep_app_searchGitHub") {
+    const query = str(input.query)
+    return {
+      icon: "◇",
+      title: query ? `Code Search "${query}"` : "Code Search",
+    }
+  }
+
+  if (toolName === "task") {
+    const desc = str(input.description)
+    const subagent = str(input.subagent_type)
+    return {
+      icon: "#",
+      title: desc || (subagent ? `${subagent} Task` : "Task"),
+      description: subagent ? `agent=${subagent}` : undefined,
+    }
+  }
+
+  if (toolName === "bash") {
+    const command = str(input.command)
+    return {
+      icon: "$",
+      title: command || "bash",
+      description: formatKeyValues(input, ["command"]),
+    }
+  }
+
+  if (toolName === "skill") {
+    const name = str(input.name)
+    return {
+      icon: "→",
+      title: name ? `Skill "${name}"` : "Skill",
+    }
+  }
+
+  if (toolName === "todowrite") {
+    return {
+      icon: "#",
+      title: "Todos",
+    }
+  }
+
+  return {
+    icon: "⚙",
+    title: toolName,
+    description: formatKeyValues(input, []),
+  }
+}
+
+function formatKeyValues(input: Record<string, unknown>, exclude: string[]): string | undefined {
+  const entries = Object.entries(input).filter(([key, value]) => {
+    if (exclude.includes(key)) return false
+    return typeof value === "string" || typeof value === "number" || typeof value === "boolean"
+  })
+  if (!entries.length) return undefined
+
+  return entries
+    .map(([key, value]) => `${key}=${String(value)}`)
+    .join(" ")
+}
+
+function str(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined
+  const trimmed = value.trim()
+  return trimmed.length ? trimmed : undefined
+}

src/cli/run/types.ts

@@ -4,8 +4,8 @@ export type { OpencodeClient }
 export interface RunOptions {
   message: string
   agent?: string
+  verbose?: boolean
   directory?: string
-  timeout?: number
   port?: number
   attach?: string
   onComplete?: string
@@ -31,6 +31,7 @@ export interface RunContext {
   sessionID: string
   directory: string
   abortController: AbortController
+  verbose?: boolean
 }
 
 export interface Todo {
@@ -66,12 +67,14 @@ export interface SessionStatusProps {
 
 export interface MessageUpdatedProps {
   info?: {
+    id?: string
     sessionID?: string
     sessionId?: string
     role?: string
     modelID?: string
     providerID?: string
     agent?: string
+    variant?: string
   }
 }
 
@@ -95,6 +98,15 @@ export interface MessagePartUpdatedProps {
   }
 }
 
+export interface MessagePartDeltaProps {
+  sessionID?: string
+  sessionId?: string
+  messageID?: string
+  partID?: string
+  field?: string
+  delta?: string
+}
+
 export interface ToolExecuteProps {
   sessionID?: string
   sessionId?: string

src/config/schema/hooks.ts

@@ -33,9 +33,11 @@ export const HookNameSchema = z.enum([
   "claude-code-hooks",
   "auto-slash-command",
   "edit-error-recovery",
+  "json-error-recovery",
   "delegate-task-retry",
   "prometheus-md-only",
   "sisyphus-junior-notepad",
+  "sisyphus-gpt-hephaestus-reminder",
   "start-work",
   "atlas",
   "unstable-agent-babysitter",

src/features/AGENTS.md

@@ -1,6 +1,6 @@
-# src/features/ — 18 Feature Modules
+# src/features/ — 19 Feature Modules
 
-**Generated:** 2026-02-17
+**Generated:** 2026-02-18
 
 ## OVERVIEW
 
@@ -27,6 +27,7 @@ Standalone feature modules wired into plugin/ layer. Each is self-contained with
 | **claude-code-agent-loader** | 3 | LOW | Load agents from .opencode/agents/ |
 | **claude-code-command-loader** | 3 | LOW | Load commands from .opencode/commands/ |
 | **claude-code-session-state** | 2 | LOW | Subagent session state tracking |
+| **run-continuation-state** | 5 | LOW | Persistent state for `run` command continuation across sessions |
 | **tool-metadata-store** | 2 | LOW | Tool execution metadata cache |
 
 ## KEY MODULES

src/features/background-agent/AGENTS.md

@@ -0,0 +1,56 @@
+# src/features/background-agent/ — Core Orchestration Engine
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+39 files (~10k LOC). Manages async task lifecycle: launch → queue → run → poll → complete/error. Concurrency limited per model/provider (default 5). Central to multi-agent orchestration.
+
+## TASK LIFECYCLE
+
+```
+LaunchInput → pending → [ConcurrencyManager queue] → running → polling → completed/error/cancelled/interrupt
+```
+
+## KEY FILES
+
+| File | Purpose |
+|------|---------|
+| `manager.ts` | `BackgroundManager` — main class: launch, cancel, getTask, listTasks |
+| `spawner.ts` | Task spawning: create session → inject prompt → start polling |
+| `concurrency.ts` | `ConcurrencyManager` — FIFO queue per concurrency key, slot acquisition/release |
+| `task-poller.ts` | 3s interval polling, completion via idle events + stability detection (10s unchanged) |
+| `result-handler.ts` | Process completed tasks: extract result, notify parent, cleanup |
+| `state.ts` | In-memory task store (Map-based) |
+| `types.ts` | `BackgroundTask`, `LaunchInput`, `ResumeInput`, `BackgroundTaskStatus` |
+
+## SPAWNER SUBDIRECTORY (6 files)
+
+| File | Purpose |
+|------|---------|
+| `spawner-context.ts` | `SpawnerContext` interface composing all spawner deps |
+| `background-session-creator.ts` | Create OpenCode session for background task |
+| `concurrency-key-from-launch-input.ts` | Derive concurrency key from model/provider |
+| `parent-directory-resolver.ts` | Resolve working directory for child session |
+| `tmux-callback-invoker.ts` | Notify TmuxSessionManager on session creation |
+
+## COMPLETION DETECTION
+
+Two signals combined:
+1. **Session idle event** — OpenCode reports session became idle
+2. **Stability detection** — message count unchanged for 10s (3+ stable polls at 3s interval)
+
+Both must agree before marking a task complete. Prevents premature completion on brief pauses.
+
+## CONCURRENCY MODEL
+
+- Key format: `{providerID}/{modelID}` (e.g., `anthropic/claude-opus-4-6`)
+- Default limit: 5 concurrent per key (configurable via `background_task` config)
+- FIFO queue: tasks wait in order when slots full
+- Slot released on: completion, error, cancellation
+
+## NOTIFICATION FLOW
+
+```
+task completed → result-handler → parent-session-notifier → inject system message into parent session
+```

src/features/mcp-oauth/callback-server.test.ts

@@ -1,38 +1,8 @@
 import { afterEach, describe, expect, it } from "bun:test"
-import { findAvailablePort, startCallbackServer, type CallbackServer } from "./callback-server"
+import { startCallbackServer, type CallbackServer } from "./callback-server"
 
 const nativeFetch = Bun.fetch.bind(Bun)
 
-describe("findAvailablePort", () => {
-  it("returns the start port when it is available", async () => {
-    // given
-    const startPort = 19877
-
-    // when
-    const port = await findAvailablePort(startPort)
-
-    // then
-    expect(port).toBeGreaterThanOrEqual(startPort)
-    expect(port).toBeLessThan(startPort + 20)
-  })
-
-  it("skips busy ports and returns next available", async () => {
-    // given
-    const blocker = Bun.serve({
-      port: 19877,
-      hostname: "127.0.0.1",
-      fetch: () => new Response(),
-    })
-
-    // when
-    const port = await findAvailablePort(19877)
-
-    // then
-    expect(port).toBeGreaterThan(19877)
-    blocker.stop(true)
-  })
-})
-
 describe("startCallbackServer", () => {
   let server: CallbackServer | null = null
 

src/features/mcp-oauth/callback-server.ts

@@ -1,5 +1,6 @@
+import { findAvailablePort as findAvailablePortShared } from "../../shared/port-utils"
+
 const DEFAULT_PORT = 19877
-const MAX_PORT_ATTEMPTS = 20
 const TIMEOUT_MS = 5 * 60 * 1000
 
 export type OAuthCallbackResult = {
@@ -33,28 +34,8 @@ const SUCCESS_HTML = `<!DOCTYPE html>
 </body>
 </html>`
 
-async function isPortAvailable(port: number): Promise<boolean> {
-  try {
-    const server = Bun.serve({
-      port,
-      hostname: "127.0.0.1",
-      fetch: () => new Response(),
-    })
-    server.stop(true)
-    return true
-  } catch {
-    return false
-  }
-}
-
 export async function findAvailablePort(startPort: number = DEFAULT_PORT): Promise<number> {
-  for (let attempt = 0; attempt < MAX_PORT_ATTEMPTS; attempt++) {
-    const port = startPort + attempt
-    if (await isPortAvailable(port)) {
-      return port
-    }
-  }
-  throw new Error(`No available port found in range ${startPort}-${startPort + MAX_PORT_ATTEMPTS - 1}`)
+  return findAvailablePortShared(startPort)
 }
 
 export async function startCallbackServer(startPort: number = DEFAULT_PORT): Promise<CallbackServer> {

src/features/opencode-skill-loader/AGENTS.md

@@ -0,0 +1,59 @@
+# src/features/opencode-skill-loader/ — 4-Scope Skill Discovery
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+28 files (~3.2k LOC). Discovers, parses, merges, and resolves SKILL.md files from 4 scopes with priority deduplication.
+
+## 4-SCOPE PRIORITY (highest → lowest)
+
+```
+1. Project (.opencode/skills/)
+2. OpenCode config (~/.config/opencode/skills/)
+3. User (~/.config/opencode/oh-my-opencode/skills/)
+4. Global (built-in skills)
+```
+
+Same-named skill at higher scope overrides lower.
+
+## KEY FILES
+
+| File | Purpose |
+|------|---------|
+| `loader.ts` | Main `loadSkills()` — orchestrates discovery → parse → merge |
+| `async-loader.ts` | Async variant for non-blocking skill loading |
+| `blocking.ts` | Sync variant for initial load |
+| `merger.ts` | Priority-based deduplication across scopes |
+| `skill-content.ts` | YAML frontmatter parsing from SKILL.md |
+| `skill-discovery.ts` | Find SKILL.md files in directory trees |
+| `skill-directory-loader.ts` | Load all skills from a single directory |
+| `config-source-discovery.ts` | Discover scope directories from config |
+| `skill-template-resolver.ts` | Variable substitution in skill templates |
+| `skill-mcp-config.ts` | Extract MCP configs from skill YAML |
+| `types.ts` | `LoadedSkill`, `SkillScope`, `SkillDiscoveryResult` |
+
+## SKILL FORMAT (SKILL.md)
+
+```markdown
+---
+name: my-skill
+description: What this skill does
+tools: [Bash, Read, Write]
+mcp:
+  - name: my-mcp
+    type: stdio
+    command: npx
+    args: [-y, my-mcp-server]
+---
+
+Skill content (instructions for the agent)...
+```
+
+## MERGER SUBDIRECTORY
+
+Handles complex merge logic when skills from multiple scopes have overlapping names or MCP configs.
+
+## TEMPLATE RESOLUTION
+
+Variables like `{{directory}}`, `{{agent}}` in skill content get resolved at load time based on current context.

src/features/run-continuation-state/constants.ts

@@ -0,0 +1 @@
+export const CONTINUATION_MARKER_DIR = ".sisyphus/run-continuation"

src/features/run-continuation-state/index.ts

@@ -0,0 +1,3 @@
+export * from "./types"
+export * from "./constants"
+export * from "./storage"

src/features/run-continuation-state/storage.test.ts

@@ -0,0 +1,91 @@
+import { afterEach, describe, expect, it } from "bun:test"
+import { mkdtempSync, rmSync } from "node:fs"
+import { join } from "node:path"
+import { tmpdir } from "node:os"
+import {
+  clearContinuationMarker,
+  isContinuationMarkerActive,
+  readContinuationMarker,
+  setContinuationMarkerSource,
+} from "./storage"
+
+const tempDirs: string[] = []
+
+function createTempDir(): string {
+  const directory = mkdtempSync(join(tmpdir(), "omo-run-marker-"))
+  tempDirs.push(directory)
+  return directory
+}
+
+afterEach(() => {
+  while (tempDirs.length > 0) {
+    const directory = tempDirs.pop()
+    if (directory) {
+      rmSync(directory, { recursive: true, force: true })
+    }
+  }
+})
+
+describe("run-continuation-state storage", () => {
+  it("stores and reads per-source marker state", () => {
+    // given
+    const directory = createTempDir()
+    const sessionID = "ses_test"
+
+    // when
+    setContinuationMarkerSource(directory, sessionID, "todo", "active", "2 todos remaining")
+    setContinuationMarkerSource(directory, sessionID, "stop", "stopped", "user requested stop")
+    const marker = readContinuationMarker(directory, sessionID)
+
+    // then
+    expect(marker).not.toBeNull()
+    expect(marker?.sessionID).toBe(sessionID)
+    expect(marker?.sources.todo?.state).toBe("active")
+    expect(marker?.sources.todo?.reason).toBe("2 todos remaining")
+    expect(marker?.sources.stop?.state).toBe("stopped")
+  })
+
+  it("treats marker as active when any source is active", () => {
+    // given
+    const directory = createTempDir()
+    const sessionID = "ses_active"
+    setContinuationMarkerSource(directory, sessionID, "todo", "active", "pending")
+    setContinuationMarkerSource(directory, sessionID, "stop", "idle")
+    const marker = readContinuationMarker(directory, sessionID)
+
+    // when
+    const isActive = isContinuationMarkerActive(marker)
+
+    // then
+    expect(isActive).toBe(true)
+  })
+
+  it("returns inactive when no source is active", () => {
+    // given
+    const directory = createTempDir()
+    const sessionID = "ses_idle"
+    setContinuationMarkerSource(directory, sessionID, "todo", "idle")
+    setContinuationMarkerSource(directory, sessionID, "stop", "stopped")
+    const marker = readContinuationMarker(directory, sessionID)
+
+    // when
+    const isActive = isContinuationMarkerActive(marker)
+
+    // then
+    expect(isActive).toBe(false)
+  })
+
+  it("clears marker for a session", () => {
+    // given
+    const directory = createTempDir()
+    const sessionID = "ses_clear"
+    setContinuationMarkerSource(directory, sessionID, "todo", "active")
+
+    // when
+    clearContinuationMarker(directory, sessionID)
+    const marker = readContinuationMarker(directory, sessionID)
+
+    // then
+    expect(marker).toBeNull()
+  })
+})

src/features/run-continuation-state/storage.ts

@@ -0,0 +1,80 @@
+import { existsSync, mkdirSync, readFileSync, rmSync, writeFileSync } from "node:fs"
+import { join } from "node:path"
+import { CONTINUATION_MARKER_DIR } from "./constants"
+import type {
+  ContinuationMarker,
+  ContinuationMarkerSource,
+  ContinuationMarkerState,
+} from "./types"
+
+function getMarkerPath(directory: string, sessionID: string): string {
+  return join(directory, CONTINUATION_MARKER_DIR, `${sessionID}.json`)
+}
+
+export function readContinuationMarker(
+  directory: string,
+  sessionID: string,
+): ContinuationMarker | null {
+  const markerPath = getMarkerPath(directory, sessionID)
+  if (!existsSync(markerPath)) return null
+
+  try {
+    const raw = readFileSync(markerPath, "utf-8")
+    const parsed = JSON.parse(raw)
+    if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) return null
+    return parsed as ContinuationMarker
+  } catch {
+    return null
+  }
+}
+
+export function setContinuationMarkerSource(
+  directory: string,
+  sessionID: string,
+  source: ContinuationMarkerSource,
+  state: ContinuationMarkerState,
+  reason?: string,
+): ContinuationMarker {
+  const now = new Date().toISOString()
+  const existing = readContinuationMarker(directory, sessionID)
+  const next: ContinuationMarker = {
+    sessionID,
+    updatedAt: now,
+    sources: {
+      ...(existing?.sources ?? {}),
+      [source]: {
+        state,
+        ...(reason ? { reason } : {}),
+        updatedAt: now,
+      },
+    },
+  }
+
+  const markerPath = getMarkerPath(directory, sessionID)
+  mkdirSync(join(directory, CONTINUATION_MARKER_DIR), { recursive: true })
+  writeFileSync(markerPath, JSON.stringify(next, null, 2), "utf-8")
+  return next
+}
+
+export function clearContinuationMarker(directory: string, sessionID: string): void {
+  const markerPath = getMarkerPath(directory, sessionID)
+  if (!existsSync(markerPath)) return
+
+  try {
+    rmSync(markerPath)
+  } catch {
+  }
+}
+
+export function isContinuationMarkerActive(marker: ContinuationMarker | null): boolean {
+  if (!marker) return false
+  return Object.values(marker.sources).some((entry) => entry?.state === "active")
+}
+
+export function getActiveContinuationMarkerReason(marker: ContinuationMarker | null): string | null {
+  if (!marker) return null
+  const active = Object.entries(marker.sources).find(([, entry]) => entry?.state === "active")
+  if (!active || !active[1]) return null
+  const [source, entry] = active
+  return entry.reason ?? `${source} continuation is active`
+}

src/features/run-continuation-state/types.ts

@@ -0,0 +1,15 @@
+export type ContinuationMarkerSource = "todo" | "stop"
+
+export type ContinuationMarkerState = "idle" | "active" | "stopped"
+
+export interface ContinuationMarkerSourceEntry {
+  state: ContinuationMarkerState
+  reason?: string
+  updatedAt: string
+}
+
+export interface ContinuationMarker {
+  sessionID: string
+  updatedAt: string
+  sources: Partial<Record<ContinuationMarkerSource, ContinuationMarkerSourceEntry>>
+}

src/features/tmux-subagent/AGENTS.md

@@ -0,0 +1,52 @@
+# src/features/tmux-subagent/ — Tmux Pane Management
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+28 files. State-first tmux integration managing panes for background agent sessions. Handles split decisions, grid planning, polling, and lifecycle events.
+
+## CORE ARCHITECTURE
+
+```
+TmuxSessionManager (manager.ts)
+  ├─→ DecisionEngine: Should we spawn/close panes?
+  ├─→ ActionExecutor: Execute spawn/close/replace actions
+  ├─→ PollingManager: Monitor pane health
+  └─→ EventHandlers: React to session create/delete
+```
+
+## KEY FILES
+
+| File | Purpose |
+|------|---------|
+| `manager.ts` | `TmuxSessionManager` — main class, session tracking, event routing |
+| `decision-engine.ts` | Evaluate window state → produce `SpawnDecision` with actions |
+| `action-executor.ts` | Execute `PaneAction[]` (close, spawn, replace) |
+| `grid-planning.ts` | Calculate pane layout given window dimensions |
+| `spawn-action-decider.ts` | Decide spawn vs replace vs skip |
+| `spawn-target-finder.ts` | Find best pane to split or replace |
+| `polling-manager.ts` | Health polling for tracked sessions |
+| `types.ts` | `TrackedSession`, `WindowState`, `PaneAction`, `SpawnDecision` |
+
+## PANE LIFECYCLE
+
+```
+session.created → spawn-action-decider → grid-planning → action-executor → track session
+session.deleted → cleanup tracked session → close pane if empty
+```
+
+## LAYOUT CONSTRAINTS
+
+- `MIN_PANE_WIDTH`: 52 chars
+- `MIN_PANE_HEIGHT`: 11 lines
+- Main pane preserved (never split below minimum)
+- Agent panes split from remaining space
+
+## EVENT HANDLERS
+
+| File | Event |
+|------|-------|
+| `session-created-handler.ts` | New background session → spawn pane |
+| `session-deleted-handler.ts` | Session ended → close pane |
+| `session-created-event.ts` | Event type definition |

src/hooks/AGENTS.md

@@ -1,14 +1,14 @@
-# src/hooks/ — 41 Lifecycle Hooks
+# src/hooks/ — 44 Lifecycle Hooks
 
-**Generated:** 2026-02-17
+**Generated:** 2026-02-18
 
 ## OVERVIEW
 
-41 hooks across 37 directories + 6 standalone files. Three-tier composition: Core(33) + Continuation(7) + Skill(2). All hooks follow `createXXXHook(deps) → HookFunction` factory pattern.
+44 hooks across 39 directories + 6 standalone files. Three-tier composition: Core(35) + Continuation(7) + Skill(2). All hooks follow `createXXXHook(deps) → HookFunction` factory pattern.
 
 ## HOOK TIERS
 
-### Tier 1: Session Hooks (20) — `create-session-hooks.ts`
+### Tier 1: Session Hooks (22) — `create-session-hooks.ts`
 
 | Hook | Event | Purpose |
 |------|-------|---------|
@@ -31,6 +31,9 @@
 | questionLabelTruncator | tool.execute.before | Truncate long question labels |
 | taskResumeInfo | chat.message | Inject task context on resume |
 | anthropicEffort | chat.params | Adjust reasoning effort level |
+| jsonErrorRecovery | tool.execute.after | Detect JSON parse errors, inject correction reminder |
+| sisyphusGptHephaestusReminder | chat.message | Toast warning when Sisyphus uses GPT model |
+| taskReminder | tool.execute.after | Remind about task tools after 10 turns without usage |
 
 ### Tier 2: Tool Guard Hooks (9) — `create-tool-guard-hooks.ts`
 

src/hooks/anthropic-context-window-limit-recovery/AGENTS.md

@@ -0,0 +1,49 @@
+# src/hooks/anthropic-context-window-limit-recovery/ — Multi-Strategy Context Recovery
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+31 files (~2232 LOC). Most complex hook. Recovers from context window limit errors via multiple strategies applied in sequence.
+
+## RECOVERY STRATEGIES (in priority order)
+
+| Strategy | File | Mechanism |
+|----------|------|-----------|
+| **Empty content recovery** | `empty-content-recovery.ts` | Handle empty/null content blocks in messages |
+| **Deduplication** | `deduplication-recovery.ts` | Remove duplicate tool results from context |
+| **Target-token truncation** | `target-token-truncation.ts` | Truncate largest tool outputs to fit target ratio |
+| **Aggressive truncation** | `aggressive-truncation-strategy.ts` | Last-resort truncation with minimal output preservation |
+| **Summarize retry** | `summarize-retry-strategy.ts` | Compaction + summarization then retry |
+
+## KEY FILES
+
+| File | Purpose |
+|------|---------|
+| `recovery-hook.ts` | Main hook entry — `session.error` handler, strategy orchestration |
+| `executor.ts` | Execute recovery strategies in sequence |
+| `parser.ts` | Parse Anthropic token limit error messages |
+| `state.ts` | `AutoCompactState` — per-session retry/truncation tracking |
+| `types.ts` | `ParsedTokenLimitError`, `RetryState`, `TruncateState`, config constants |
+| `storage.ts` | Persist tool results for later truncation |
+| `tool-result-storage.ts` | Store/retrieve individual tool call results |
+| `message-builder.ts` | Build retry messages after recovery |
+
+## RETRY CONFIG
+
+- Max attempts: 2
+- Initial delay: 2s, backoff ×2, max 30s
+- Max truncation attempts: 20
+- Target token ratio: 0.5 (truncate to 50% of limit)
+- Chars per token estimate: 4
+
+## PRUNING SYSTEM
+
+`pruning-*.ts` files handle intelligent output pruning:
+- `pruning-deduplication.ts` — Remove duplicate content across tool results
+- `pruning-tool-output-truncation.ts` — Truncate oversized tool outputs
+- `pruning-types.ts` — Pruning-specific type definitions
+
+## SDK VARIANTS
+
+`empty-content-recovery-sdk.ts` and `tool-result-storage-sdk.ts` provide SDK-based implementations for OpenCode client interactions.

src/hooks/index.ts

@@ -27,8 +27,10 @@ export { createInteractiveBashSessionHook } from "./interactive-bash-session";
 export { createThinkingBlockValidatorHook } from "./thinking-block-validator";
 export { createCategorySkillReminderHook } from "./category-skill-reminder";
 export { createRalphLoopHook, type RalphLoopHook } from "./ralph-loop";
+export { createSisyphusGptHephaestusReminderHook } from "./sisyphus-gpt-hephaestus-reminder";
 export { createAutoSlashCommandHook } from "./auto-slash-command";
 export { createEditErrorRecoveryHook } from "./edit-error-recovery";
+export { createJsonErrorRecoveryHook } from "./json-error-recovery";
 export { createPrometheusMdOnlyHook } from "./prometheus-md-only";
 export { createSisyphusJuniorNotepadHook } from "./sisyphus-junior-notepad";
 export { createTaskResumeInfoHook } from "./task-resume-info";

src/hooks/json-error-recovery/hook.ts

@@ -0,0 +1,58 @@
+import type { PluginInput } from "@opencode-ai/plugin"
+
+export const JSON_ERROR_TOOL_EXCLUDE_LIST = [
+  "bash",
+  "read",
+  "glob",
+  "grep",
+  "webfetch",
+  "look_at",
+  "grep_app_searchgithub",
+  "websearch_web_search_exa",
+] as const
+
+export const JSON_ERROR_PATTERNS = [
+  /json parse error/i,
+  /failed to parse json/i,
+  /invalid json/i,
+  /malformed json/i,
+  /unexpected end of json input/i,
+  /syntaxerror:\s*unexpected token.*json/i,
+  /json[^\n]*expected '\}'/i,
+  /json[^\n]*unexpected eof/i,
+] as const
+
+const JSON_ERROR_REMINDER_MARKER = "[JSON PARSE ERROR - IMMEDIATE ACTION REQUIRED]"
+const JSON_ERROR_EXCLUDED_TOOLS = new Set<string>(JSON_ERROR_TOOL_EXCLUDE_LIST)
+
+export const JSON_ERROR_REMINDER = `
+[JSON PARSE ERROR - IMMEDIATE ACTION REQUIRED]
+
+You sent invalid JSON arguments. The system could not parse your tool call.
+STOP and do this NOW:
+
+1. LOOK at the error message above to see what was expected vs what you sent.
+2. CORRECT your JSON syntax (missing braces, unescaped quotes, trailing commas, etc).
+3. RETRY the tool call with valid JSON.
+
+DO NOT repeat the exact same invalid call.
+`
+
+export function createJsonErrorRecoveryHook(_ctx: PluginInput) {
+  return {
+    "tool.execute.after": async (
+      input: { tool: string; sessionID: string; callID: string },
+      output: { title: string; output: string; metadata: unknown }
+    ) => {
+      if (JSON_ERROR_EXCLUDED_TOOLS.has(input.tool.toLowerCase())) return
+      if (typeof output.output !== "string") return
+      if (output.output.includes(JSON_ERROR_REMINDER_MARKER)) return
+
+      const hasJsonError = JSON_ERROR_PATTERNS.some((pattern) => pattern.test(output.output))
+
+      if (hasJsonError) {
+        output.output += `\n${JSON_ERROR_REMINDER}`
+      }
+    },
+  }
+}

src/hooks/json-error-recovery/index.test.ts

@@ -0,0 +1,196 @@
+import { beforeEach, describe, expect, it } from "bun:test"
+import type { PluginInput } from "@opencode-ai/plugin"
+
+import {
+  createJsonErrorRecoveryHook,
+  JSON_ERROR_PATTERNS,
+  JSON_ERROR_REMINDER,
+  JSON_ERROR_TOOL_EXCLUDE_LIST,
+} from "./index"
+
+describe("createJsonErrorRecoveryHook", () => {
+  let hook: ReturnType<typeof createJsonErrorRecoveryHook>
+
+  type ToolExecuteAfterHandler = NonNullable<
+    ReturnType<typeof createJsonErrorRecoveryHook>["tool.execute.after"]
+  >
+  type ToolExecuteAfterInput = Parameters<ToolExecuteAfterHandler>[0]
+  type ToolExecuteAfterOutput = Parameters<ToolExecuteAfterHandler>[1]
+
+  const createMockPluginInput = (): PluginInput => {
+    return {
+      client: {} as PluginInput["client"],
+      directory: "/tmp/test",
+    } as PluginInput
+  }
+
+  beforeEach(() => {
+    hook = createJsonErrorRecoveryHook(createMockPluginInput())
+  })
+
+  describe("tool.execute.after", () => {
+    const createInput = (tool = "Edit"): ToolExecuteAfterInput => ({
+      tool,
+      sessionID: "test-session",
+      callID: "test-call-id",
+    })
+
+    const createOutput = (outputText: string): ToolExecuteAfterOutput => ({
+      title: "Tool Error",
+      output: outputText,
+      metadata: {},
+    })
+
+    const createUnknownOutput = (value: unknown): { title: string; output: unknown; metadata: Record<string, unknown> } => ({
+      title: "Tool Error",
+      output: value,
+      metadata: {},
+    })
+
+    it("appends reminder when output includes JSON parse error", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput("JSON parse error: expected '}' in JSON body")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      expect(output.output).toContain(JSON_ERROR_REMINDER)
+    })
+
+    it("appends reminder when output includes SyntaxError", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput("SyntaxError: Unexpected token in JSON at position 10")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      expect(output.output).toContain(JSON_ERROR_REMINDER)
+    })
+
+    it("does not append reminder for normal output", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput("Task completed successfully")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      expect(output.output).toBe("Task completed successfully")
+    })
+
+    it("does not append reminder for empty output", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput("")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      expect(output.output).toBe("")
+    })
+
+    it("does not append reminder for false positive non-JSON text", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput("Template failed: expected '}' before newline")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      expect(output.output).toBe("Template failed: expected '}' before newline")
+    })
+
+    it("does not append reminder for excluded tools", async () => {
+      // given
+      const input = createInput("Read")
+      const output = createOutput("JSON parse error: unexpected end of JSON input")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      expect(output.output).toBe("JSON parse error: unexpected end of JSON input")
+    })
+
+    it("does not append reminder when reminder already exists", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput(`JSON parse error: invalid JSON\n${JSON_ERROR_REMINDER}`)
+
+      // when
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      const reminderCount = output.output.split("[JSON PARSE ERROR - IMMEDIATE ACTION REQUIRED]").length - 1
+      expect(reminderCount).toBe(1)
+    })
+
+    it("does not append duplicate reminder on repeated execution", async () => {
+      // given
+      const input = createInput()
+      const output = createOutput("JSON parse error: invalid JSON arguments")
+
+      // when
+      await hook["tool.execute.after"](input, output)
+      await hook["tool.execute.after"](input, output)
+
+      // then
+      const reminderCount = output.output.split("[JSON PARSE ERROR - IMMEDIATE ACTION REQUIRED]").length - 1
+      expect(reminderCount).toBe(1)
+    })
+
+    it("ignores non-string output values", async () => {
+      // given
+      const input = createInput()
+      const values: unknown[] = [42, null, undefined, { error: "invalid json" }]
+
+      // when
+      for (const value of values) {
+        const output = createUnknownOutput(value)
+        await hook["tool.execute.after"](input, output as ToolExecuteAfterOutput)
+
+        // then
+        expect(output.output).toBe(value)
+      }
+    })
+  })
+
+  describe("JSON_ERROR_PATTERNS", () => {
+    it("contains known parse error patterns", () => {
+      // given
+      const output = "JSON parse error: unexpected end of JSON input"
+
+      // when
+      const isMatched = JSON_ERROR_PATTERNS.some((pattern) => pattern.test(output))
+
+      // then
+      expect(isMatched).toBe(true)
+    })
+  })
+
+  describe("JSON_ERROR_TOOL_EXCLUDE_LIST", () => {
+    it("contains content-heavy tools that should be excluded", () => {
+      // given
+      const expectedExcludedTools: Array<(typeof JSON_ERROR_TOOL_EXCLUDE_LIST)[number]> = [
+        "read",
+        "bash",
+        "webfetch",
+      ]
+
+      // when
+      const allExpectedToolsIncluded = expectedExcludedTools.every((toolName) =>
+        JSON_ERROR_TOOL_EXCLUDE_LIST.includes(toolName)
+      )
+
+      // then
+      expect(allExpectedToolsIncluded).toBe(true)
+    })
+  })
+})

src/hooks/json-error-recovery/index.ts

@@ -0,0 +1,6 @@
+export {
+  createJsonErrorRecoveryHook,
+  JSON_ERROR_TOOL_EXCLUDE_LIST,
+  JSON_ERROR_PATTERNS,
+  JSON_ERROR_REMINDER,
+} from "./hook"

src/hooks/sisyphus-gpt-hephaestus-reminder/hook.ts

@@ -0,0 +1,37 @@
+import type { PluginInput } from "@opencode-ai/plugin"
+import { getSessionAgent } from "../../features/claude-code-session-state"
+import { log } from "../../shared"
+
+const TOAST_TITLE = "Use Hephaestus for GPT Models"
+const TOAST_MESSAGE = "Sisyphus is using a GPT model. Use Hephaestus and include 'ulw' in your prompt."
+
+export function createSisyphusGptHephaestusReminderHook(ctx: PluginInput) {
+  return {
+    "chat.message": async (input: {
+      sessionID: string
+      agent?: string
+      model?: { providerID: string; modelID: string }
+    }): Promise<void> => {
+      const agentName = (input.agent ?? getSessionAgent(input.sessionID) ?? "").toLowerCase()
+      const modelID = input.model?.modelID?.toLowerCase() ?? ""
+
+      if (agentName !== "sisyphus" || !modelID.includes("gpt")) {
+        return
+      }
+
+      await ctx.client.tui.showToast({
+        body: {
+          title: TOAST_TITLE,
+          message: TOAST_MESSAGE,
+          variant: "error",
+          duration: 5000,
+        },
+      }).catch((error) => {
+        log("[sisyphus-gpt-hephaestus-reminder] Failed to show toast", {
+          sessionID: input.sessionID,
+          error,
+        })
+      })
+    },
+  }
+}

src/hooks/sisyphus-gpt-hephaestus-reminder/index.test.ts

@@ -0,0 +1,78 @@
+import { describe, expect, test, spyOn } from "bun:test"
+import { createSisyphusGptHephaestusReminderHook } from "./index"
+import { _resetForTesting, updateSessionAgent } from "../../features/claude-code-session-state"
+
+describe("sisyphus-gpt-hephaestus-reminder hook", () => {
+  test("shows error toast when sisyphus uses gpt model", async () => {
+    // given - sisyphus agent with gpt model
+    const showToast = spyOn({
+      fn: async () => ({}),
+    }, "fn")
+    const hook = createSisyphusGptHephaestusReminderHook({
+      client: {
+        tui: { showToast },
+      },
+    } as any)
+
+    // when - chat.message runs
+    await hook["chat.message"]?.({
+      sessionID: "ses_1",
+      agent: "sisyphus",
+      model: { providerID: "openai", modelID: "gpt-5.3-codex" },
+    })
+
+    // then - error toast is shown
+    expect(showToast).toHaveBeenCalledTimes(1)
+    expect(showToast.mock.calls[0]?.[0]).toMatchObject({
+      body: {
+        title: "Use Hephaestus for GPT Models",
+        variant: "error",
+      },
+    })
+  })
+
+  test("does not show toast for non-gpt model", async () => {
+    // given - sisyphus agent with non-gpt model
+    const showToast = spyOn({
+      fn: async () => ({}),
+    }, "fn")
+    const hook = createSisyphusGptHephaestusReminderHook({
+      client: {
+        tui: { showToast },
+      },
+    } as any)
+
+    // when - chat.message runs with claude model
+    await hook["chat.message"]?.({
+      sessionID: "ses_2",
+      agent: "sisyphus",
+      model: { providerID: "anthropic", modelID: "claude-opus-4-6" },
+    })
+
+    // then - no toast
+    expect(showToast).toHaveBeenCalledTimes(0)
+  })
+
+  test("uses session agent fallback when input agent is missing", async () => {
+    // given - session agent saved as sisyphus
+    _resetForTesting()
+    updateSessionAgent("ses_3", "sisyphus")
+    const showToast = spyOn({
+      fn: async () => ({}),
+    }, "fn")
+    const hook = createSisyphusGptHephaestusReminderHook({
+      client: {
+        tui: { showToast },
+      },
+    } as any)
+
+    // when - chat.message runs without input.agent
+    await hook["chat.message"]?.({
+      sessionID: "ses_3",
+      model: { providerID: "openai", modelID: "gpt-5.2" },
+    })
+
+    // then - toast shown via fallback agent lookup
+    expect(showToast).toHaveBeenCalledTimes(1)
+  })
+})

src/hooks/sisyphus-gpt-hephaestus-reminder/index.ts

@@ -0,0 +1 @@
+export { createSisyphusGptHephaestusReminderHook } from "./hook"

src/hooks/stop-continuation-guard/hook.ts

@@ -1,5 +1,9 @@
 import type { PluginInput } from "@opencode-ai/plugin"
 
+import {
+  clearContinuationMarker,
+  setContinuationMarkerSource,
+} from "../../features/run-continuation-state"
 import { log } from "../../shared/logger"
 
 const HOOK_NAME = "stop-continuation-guard"
@@ -13,12 +17,13 @@ export interface StopContinuationGuard {
 }
 
 export function createStopContinuationGuardHook(
-  _ctx: PluginInput
+  ctx: PluginInput
 ): StopContinuationGuard {
   const stoppedSessions = new Set<string>()
 
   const stop = (sessionID: string): void => {
     stoppedSessions.add(sessionID)
+    setContinuationMarkerSource(ctx.directory, sessionID, "stop", "stopped", "continuation stopped")
     log(`[${HOOK_NAME}] Continuation stopped for session`, { sessionID })
   }
 
@@ -28,6 +33,7 @@ export function createStopContinuationGuardHook(
 
   const clear = (sessionID: string): void => {
     stoppedSessions.delete(sessionID)
+    setContinuationMarkerSource(ctx.directory, sessionID, "stop", "idle")
     log(`[${HOOK_NAME}] Continuation guard cleared for session`, { sessionID })
   }
 
@@ -42,6 +48,7 @@ export function createStopContinuationGuardHook(
       const sessionInfo = props?.info as { id?: string } | undefined
       if (sessionInfo?.id) {
         clear(sessionInfo.id)
+        clearContinuationMarker(ctx.directory, sessionInfo.id)
         log(`[${HOOK_NAME}] Session deleted: cleaned up`, { sessionID: sessionInfo.id })
       }
     }

src/hooks/stop-continuation-guard/index.test.ts

@@ -1,7 +1,28 @@
-import { describe, expect, test } from "bun:test"
+import { afterEach, describe, expect, test } from "bun:test"
+import { mkdtempSync, rmSync } from "node:fs"
+import { join } from "node:path"
+import { tmpdir } from "node:os"
+import { readContinuationMarker } from "../../features/run-continuation-state"
 import { createStopContinuationGuardHook } from "./index"
 
 describe("stop-continuation-guard", () => {
+  const tempDirs: string[] = []
+
+  function createTempDir(): string {
+    const directory = mkdtempSync(join(tmpdir(), "omo-stop-guard-"))
+    tempDirs.push(directory)
+    return directory
+  }
+
+  afterEach(() => {
+    while (tempDirs.length > 0) {
+      const directory = tempDirs.pop()
+      if (directory) {
+        rmSync(directory, { recursive: true, force: true })
+      }
+    }
+  })
+
   function createMockPluginInput() {
     return {
       client: {
@@ -9,13 +30,14 @@ describe("stop-continuation-guard", () => {
           showToast: async () => ({}),
         },
       },
-      directory: "/tmp/test",
-    } as never
+      directory: createTempDir(),
+    } as any
   }
 
   test("should mark session as stopped", () => {
     // given - a guard hook with no stopped sessions
-    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const input = createMockPluginInput()
+    const guard = createStopContinuationGuardHook(input)
     const sessionID = "test-session-1"
 
     // when - we stop continuation for the session
@@ -23,6 +45,9 @@ describe("stop-continuation-guard", () => {
 
     // then - session should be marked as stopped
     expect(guard.isStopped(sessionID)).toBe(true)
+
+    const marker = readContinuationMarker(input.directory, sessionID)
+    expect(marker?.sources.stop?.state).toBe("stopped")
   })
 
   test("should return false for non-stopped sessions", () => {

src/hooks/todo-continuation-enforcer/handler.ts

@@ -1,6 +1,9 @@
 import type { PluginInput } from "@opencode-ai/plugin"
 
 import type { BackgroundManager } from "../../features/background-agent"
+import {
+  clearContinuationMarker,
+} from "../../features/run-continuation-state"
 import { log } from "../../shared/logger"
 
 import { DEFAULT_SKIP_AGENTS, HOOK_NAME } from "./constants"
@@ -45,6 +48,7 @@ export function createTodoContinuationHandler(args: {
     if (event.type === "session.idle") {
       const sessionID = props?.sessionID as string | undefined
       if (!sessionID) return
+
       await handleSessionIdle({
         ctx,
         sessionID,
@@ -56,6 +60,13 @@ export function createTodoContinuationHandler(args: {
       return
     }
 
+    if (event.type === "session.deleted") {
+      const sessionInfo = props?.info as { id?: string } | undefined
+      if (sessionInfo?.id) {
+        clearContinuationMarker(ctx.directory, sessionInfo.id)
+      }
+    }
+
     handleNonIdleEvent({
       eventType: event.type,
       properties: props,

src/plugin-handlers/agent-config-handler.ts

@@ -23,9 +23,12 @@ type AgentConfigRecord = Record<string, Record<string, unknown> | undefined> & {
   plan?: Record<string, unknown>;
 };
 
-function hasConfiguredDefaultAgent(config: Record<string, unknown>): boolean {
+function getConfiguredDefaultAgent(config: Record<string, unknown>): string | undefined {
   const defaultAgent = config.default_agent;
-  return typeof defaultAgent === "string" && defaultAgent.trim().length > 0;
+  if (typeof defaultAgent !== "string") return undefined;
+
+  const trimmedDefaultAgent = defaultAgent.trim();
+  return trimmedDefaultAgent.length > 0 ? trimmedDefaultAgent : undefined;
 }
 
 export async function applyAgentConfig(params: {
@@ -107,11 +110,15 @@ export async function applyAgentConfig(params: {
   const plannerEnabled = params.pluginConfig.sisyphus_agent?.planner_enabled ?? true;
   const replacePlan = params.pluginConfig.sisyphus_agent?.replace_plan ?? true;
   const shouldDemotePlan = plannerEnabled && replacePlan;
+  const configuredDefaultAgent = getConfiguredDefaultAgent(params.config);
 
   const configAgent = params.config.agent as AgentConfigRecord | undefined;
 
   if (isSisyphusEnabled && builtinAgents.sisyphus) {
-    if (!hasConfiguredDefaultAgent(params.config)) {
+    if (configuredDefaultAgent) {
+      (params.config as { default_agent?: string }).default_agent =
+        getAgentDisplayName(configuredDefaultAgent);
+    } else {
       (params.config as { default_agent?: string }).default_agent =
         getAgentDisplayName("sisyphus");
     }

src/plugin-handlers/config-handler.test.ts

@@ -350,7 +350,55 @@ describe("Agent permission defaults", () => {
 })
 
 describe("default_agent behavior with Sisyphus orchestration", () => {
-  test("preserves existing default_agent when already set", async () => {
+  test("canonicalizes configured default_agent with surrounding whitespace", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-6",
+      default_agent: "  hephaestus  ",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.default_agent).toBe(getAgentDisplayName("hephaestus"))
+  })
+
+  test("canonicalizes configured default_agent when key uses mixed case", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-6",
+      default_agent: "HePhAeStUs",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.default_agent).toBe(getAgentDisplayName("hephaestus"))
+  })
+
+  test("canonicalizes configured default_agent key to display name", async () => {
     // #given
     const pluginConfig: OhMyOpenCodeConfig = {}
     const config: Record<string, unknown> = {
@@ -371,7 +419,32 @@ describe("default_agent behavior with Sisyphus orchestration", () => {
     await handler(config)
 
     // #then
-    expect(config.default_agent).toBe("hephaestus")
+    expect(config.default_agent).toBe(getAgentDisplayName("hephaestus"))
+  })
+
+  test("preserves existing display-name default_agent", async () => {
+    // #given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const displayName = getAgentDisplayName("hephaestus")
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-6",
+      default_agent: displayName,
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // #when
+    await handler(config)
+
+    // #then
+    expect(config.default_agent).toBe(displayName)
   })
 
   test("sets default_agent to sisyphus when missing", async () => {
@@ -396,6 +469,82 @@ describe("default_agent behavior with Sisyphus orchestration", () => {
     // #then
     expect(config.default_agent).toBe(getAgentDisplayName("sisyphus"))
   })
+
+  test("sets default_agent to sisyphus when configured default_agent is empty after trim", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-6",
+      default_agent: "    ",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.default_agent).toBe(getAgentDisplayName("sisyphus"))
+  })
+
+  test("preserves custom default_agent names while trimming whitespace", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-6",
+      default_agent: "  Custom Agent  ",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.default_agent).toBe("Custom Agent")
+  })
+
+  test("does not normalize configured default_agent when Sisyphus is disabled", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {
+      sisyphus_agent: {
+        disabled: true,
+      },
+    }
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-6",
+      default_agent: "  HePhAeStUs  ",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.default_agent).toBe("  HePhAeStUs  ")
+  })
 })
 
 describe("Prometheus category config resolution", () => {

src/plugin/AGENTS.md

@@ -0,0 +1,49 @@
+# src/plugin/ — 8 OpenCode Hook Handlers + Hook Composition
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+Core glue layer. 20 source files assembling the 8 OpenCode hook handlers and composing 44 hooks into the PluginInterface. Every handler file corresponds to one OpenCode hook type.
+
+## HANDLER FILES
+
+| File | OpenCode Hook | Purpose |
+|------|---------------|---------|
+| `chat-message.ts` | `chat.message` | First-message variant, session setup, keyword detection |
+| `chat-params.ts` | `chat.params` | Anthropic effort level, think mode |
+| `event.ts` | `event` | Session lifecycle (created, deleted, idle, error) |
+| `tool-execute-before.ts` | `tool.execute.before` | Pre-tool guards (file guard, label truncator, rules injector) |
+| `tool-execute-after.ts` | `tool.execute.after` | Post-tool hooks (output truncation, comment checker, metadata) |
+| `messages-transform.ts` | `experimental.chat.messages.transform` | Context injection, thinking block validation |
+| `tool-registry.ts` | `tool` | 26 tools assembled from factories |
+| `skill-context.ts` | — | Skill/browser/category context for tool creation |
+
+## HOOK COMPOSITION (hooks/ subdir)
+
+| File | Tier | Count |
+|------|------|-------|
+| `create-session-hooks.ts` | Session | 22 |
+| `create-tool-guard-hooks.ts` | Tool Guard | 9 |
+| `create-transform-hooks.ts` | Transform | 4 |
+| `create-continuation-hooks.ts` | Continuation | 7 |
+| `create-skill-hooks.ts` | Skill | 2 |
+| `create-core-hooks.ts` | Aggregator | Session + Guard + Transform = 35 |
+
+## SUPPORT FILES
+
+| File | Purpose |
+|------|---------|
+| `available-categories.ts` | Build `AvailableCategory[]` for agent prompt injection |
+| `session-agent-resolver.ts` | Resolve which agent owns a session |
+| `session-status-normalizer.ts` | Normalize session status across OpenCode versions |
+| `recent-synthetic-idles.ts` | Dedup rapid idle events |
+| `unstable-agent-babysitter.ts` | Track unstable agent behavior across sessions |
+| `types.ts` | `PluginContext`, `PluginInterface`, `ToolsRecord`, `TmuxConfig` |
+
+## KEY PATTERNS
+
+- Each handler exports a function receiving `(hookRecord, ctx, pluginConfig, managers)` → returns OpenCode hook function
+- Handlers iterate over hook records, calling each hook with `(input, output)` in sequence
+- `safeHook()` wrapper in composition files catches errors per-hook without breaking the chain
+- Tool registry uses `filterDisabledTools()` before returning

src/plugin/chat-message.ts

@@ -81,6 +81,7 @@ export function createChatMessageHandler(args: {
     await hooks.keywordDetector?.["chat.message"]?.(input, output)
     await hooks.claudeCodeHooks?.["chat.message"]?.(input, output)
     await hooks.autoSlashCommand?.["chat.message"]?.(input, output)
+    await hooks.sisyphusGptHephaestusReminder?.["chat.message"]?.(input)
     if (hooks.startWork && isStartWorkHookOutput(output)) {
       await hooks.startWork["chat.message"]?.(input, output)
     }

src/plugin/hooks/create-session-hooks.ts

@@ -14,11 +14,13 @@ import {
   createInteractiveBashSessionHook,
   createRalphLoopHook,
   createEditErrorRecoveryHook,
+  createJsonErrorRecoveryHook,
   createDelegateTaskRetryHook,
   createTaskResumeInfoHook,
   createStartWorkHook,
   createPrometheusMdOnlyHook,
   createSisyphusJuniorNotepadHook,
+  createSisyphusGptHephaestusReminderHook,
   createQuestionLabelTruncatorHook,
   createPreemptiveCompactionHook,
 } from "../../hooks"
@@ -44,10 +46,12 @@ export type SessionHooks = {
   interactiveBashSession: ReturnType<typeof createInteractiveBashSessionHook> | null
   ralphLoop: ReturnType<typeof createRalphLoopHook> | null
   editErrorRecovery: ReturnType<typeof createEditErrorRecoveryHook> | null
+  jsonErrorRecovery: ReturnType<typeof createJsonErrorRecoveryHook> | null
   delegateTaskRetry: ReturnType<typeof createDelegateTaskRetryHook> | null
   startWork: ReturnType<typeof createStartWorkHook> | null
   prometheusMdOnly: ReturnType<typeof createPrometheusMdOnlyHook> | null
   sisyphusJuniorNotepad: ReturnType<typeof createSisyphusJuniorNotepadHook> | null
+  sisyphusGptHephaestusReminder: ReturnType<typeof createSisyphusGptHephaestusReminderHook> | null
   questionLabelTruncator: ReturnType<typeof createQuestionLabelTruncatorHook>
   taskResumeInfo: ReturnType<typeof createTaskResumeInfoHook>
   anthropicEffort: ReturnType<typeof createAnthropicEffortHook> | null
@@ -134,6 +138,10 @@ export function createSessionHooks(args: {
     ? safeHook("edit-error-recovery", () => createEditErrorRecoveryHook(ctx))
     : null
 
+  const jsonErrorRecovery = isHookEnabled("json-error-recovery")
+    ? safeHook("json-error-recovery", () => createJsonErrorRecoveryHook(ctx))
+    : null
+
   const delegateTaskRetry = isHookEnabled("delegate-task-retry")
     ? safeHook("delegate-task-retry", () => createDelegateTaskRetryHook(ctx))
     : null
@@ -150,6 +158,10 @@ export function createSessionHooks(args: {
     ? safeHook("sisyphus-junior-notepad", () => createSisyphusJuniorNotepadHook(ctx))
     : null
 
+  const sisyphusGptHephaestusReminder = isHookEnabled("sisyphus-gpt-hephaestus-reminder")
+    ? safeHook("sisyphus-gpt-hephaestus-reminder", () => createSisyphusGptHephaestusReminderHook(ctx))
+    : null
+
   const questionLabelTruncator = createQuestionLabelTruncatorHook()
   const taskResumeInfo = createTaskResumeInfoHook()
 
@@ -170,10 +182,12 @@ export function createSessionHooks(args: {
     interactiveBashSession,
     ralphLoop,
     editErrorRecovery,
+    jsonErrorRecovery,
     delegateTaskRetry,
     startWork,
     prometheusMdOnly,
     sisyphusJuniorNotepad,
+    sisyphusGptHephaestusReminder,
     questionLabelTruncator,
     taskResumeInfo,
     anthropicEffort,

src/plugin/tool-execute-after.ts

@@ -40,6 +40,7 @@ export function createToolExecuteAfterHandler(args: {
     await hooks.categorySkillReminder?.["tool.execute.after"]?.(input, output)
     await hooks.interactiveBashSession?.["tool.execute.after"]?.(input, output)
     await hooks.editErrorRecovery?.["tool.execute.after"]?.(input, output)
+    await hooks.jsonErrorRecovery?.["tool.execute.after"]?.(input, output)
     await hooks.delegateTaskRetry?.["tool.execute.after"]?.(input, output)
     await hooks.atlasHook?.["tool.execute.after"]?.(input, output)
     await hooks.taskResumeInfo?.["tool.execute.after"]?.(input, output)

src/tools/delegate-task/AGENTS.md

@@ -0,0 +1,58 @@
+# src/tools/delegate-task/ — Task Delegation Engine
+
+**Generated:** 2026-02-18
+
+## OVERVIEW
+
+41 files. The `task` tool implementation — delegates work to subagents via background or sync sessions. Resolves categories, models, skills, and manages both async and synchronous execution flows.
+
+## TWO EXECUTION MODES
+
+| Mode | Flow | Use Case |
+|------|------|----------|
+| **Background** (`run_in_background=true`) | Launch → BackgroundManager → poll → notify parent | Explore, librarian, parallel work |
+| **Sync** (`run_in_background=false`) | Create session → send prompt → poll until idle → return result | Sequential tasks needing immediate result |
+
+## KEY FILES
+
+| File | Purpose |
+|------|---------|
+| `tools.ts` | `createDelegateTask()` factory — main entry point |
+| `executor.ts` | Route to background or sync execution |
+| `types.ts` | `DelegateTaskArgs`, `DelegateTaskToolOptions`, `ToolContextWithMetadata` |
+| `category-resolver.ts` | Map category name → model + config |
+| `subagent-resolver.ts` | Map subagent_type → agent + model |
+| `model-selection.ts` | Model availability checking + fallback |
+| `skill-resolver.ts` | Resolve `load_skills[]` → skill content for injection |
+| `prompt-builder.ts` | Build system/user prompt with skill content, categories |
+
+## SYNC EXECUTION CHAIN
+
+```
+sync-task.ts → sync-session-creator.ts → sync-prompt-sender.ts → sync-session-poller.ts → sync-result-fetcher.ts
+```
+
+Each file handles one step. `sync-continuation.ts` handles session continuation (resume with session_id).
+
+## BACKGROUND EXECUTION
+
+```
+background-task.ts → BackgroundManager.launch() → (async polling) → background-continuation.ts
+```
+
+`background-continuation.ts` handles `session_id` resume for existing background tasks.
+
+## CATEGORY RESOLUTION
+
+1. Check user-defined categories (`pluginConfig.categories`)
+2. Fall back to built-in 8 categories
+3. Resolve model from category config
+4. Check model availability → fallback if unavailable
+
+## MODEL STRING PARSER
+
+`model-string-parser.ts` handles `"model variant"` format (e.g., `"gpt-5.3-codex medium"` → model=`gpt-5.3-codex`, variant=`medium`).
+
+## UNSTABLE AGENT TRACKING
+
+`unstable-agent-task.ts` marks tasks from categories/agents known to be unstable (e.g., free models). Enables `unstableAgentBabysitter` hook monitoring.