wogiflow 2.3.0 → 2.3.2

package/.claude/commands/wogi-epics.md

@@ -148,6 +148,22 @@ This means after creating an epic with stories, you don't need to manually start
 
 **To disable**: Set `config.bulkOrchestrator.enabled: false`
 
+## Anti-Deferral Rule (MANDATORY)
+
+**When creating an epic from user input, EVERY item the user provided MUST become a tracked story.**
+
+You must NEVER:
+- Create stories for items 1-5 and silently skip items 6-9 because you judged them as "enhancements"
+- Label items as "deferred" or "long-term" and exclude them from the epic
+- Apply your own priority filter to decide which items deserve tasks
+
+You MAY:
+- Assign different priorities (P0/P1/P2/P3) to stories — but ALL items get stories
+- Suggest an execution order — but ALL items are tracked in the epic
+- Ask the user "Should I defer items 6-9?" — explicit user consent is the ONLY valid reason to exclude items
+
+**If the user provides 9 items, the epic MUST contain 9 stories (or items grouped into stories where every item appears as an acceptance criterion). Verify this with a reconciliation count before proceeding.**
+
 ## Tips
 
 - **Start with epics for major features** - Break down into stories before implementation

package/.claude/commands/wogi-start.md

@@ -67,9 +67,11 @@ When invoked with a **quoted request** instead of a task ID, assess intent and r
 
 ### Request Categories
 
-**Conversational follow-ups** ("yes", "go ahead", "option 2", "no", "skip that"):
+**Conversational follow-ups** ("yes", "go ahead", "continue", "option 2", "no", "skip that"):
 Look back at conversation for the pending question/proposal. Execute the implied action (affirmative) or acknowledge and ask what to do instead (negative).
 
+**"Continue" after task completion**: When the user says "continue" after a task finishes and there are more tasks in `ready.json` → **start the next task immediately**. Do NOT invoke `/wogi-pre-compact`, do NOT output a compaction summary, do NOT ask about context. Just start the next task. Compaction is the system's job — it happens automatically when needed.
+
 **Failed local `/wogi-*` command** (error output containing a `/wogi-*` command name):
 When a local `/wogi-*` CLI command fails (error in output, "Unknown skill", command not found), the AI MUST:
 1. **Stop current work** — user actions always take priority over in-progress AI work
@@ -192,6 +194,8 @@ Item Reconciliation:
 
 **Skip when**: Input has only 1-2 items, or is a task ID reference.
 
+**ANTI-DEFERRAL ENFORCEMENT**: After reconciliation, verify ALL items became tasks/criteria. If you find yourself writing "deferred", "skipped", or "not created" for ANY item — STOP. You are violating the anti-deferral rule. The user provided these items for a reason. Create tasks for ALL of them. You may suggest priority ordering (P0-P3), but you must NEVER autonomously filter items out. A large ready queue is correct behavior. A filtered queue is data loss that breaks the user's trust.
+
 ### Step 1.3: Explore Phase (MANDATORY Multi-Agent Research)
 
 **For L2+ tasks. Research is MANDATORY** — do NOT skip even if you think you know the answer.
@@ -497,7 +501,7 @@ Reflection: "Have I introduced any bugs or regressions?"
 
 **Quality gate keeps failing**: Report, attempt fix, after 3 failures suggest `/wogi-debug-hypothesis`.
 
-**Context too large**: When `config.autoCompact.betweenTasks` is true (default), compact AUTOMATICALLY between tasks — do NOT ask the user. Just do it. Mid-task: commit progress, invoke `/wogi-pre-compact` directly (don't suggest — execute).
+**Context too large**: When `config.autoCompact.betweenTasks` is true (default), compact AUTOMATICALLY between tasks — do NOT ask the user, do NOT show a summary, do NOT invoke `/wogi-pre-compact`. Just compact silently and continue with the next task. The PostCompact hook restores all state automatically. Mid-task: commit progress, compact silently, resume from checkpoint. The user should never see compaction happen — it's invisible infrastructure.
 
 ## Progress Tracking (MANDATORY for L1+ tasks)
 

package/.workflow/templates/claude-md.hbs

@@ -191,6 +191,31 @@ cat .workflow/state/decisions.md # Project rules
 
 **These apply to ALL implementation work:**
 
+### Anti-Deferral Rule (MANDATORY — ZERO TOLERANCE)
+
+**You MUST NEVER autonomously defer, skip, deprioritize, or drop items from the user's input.**
+
+If the user provides N items, ALL N must become tracked work items. No exceptions. No judgment calls about what's "important" vs. "enhancement" vs. "long-term."
+
+**Anti-Deferral Checklist** — If ANY of these thoughts cross your mind, you are about to drop items:
+- "Items 6-9 are enhancements, I'll focus on the fixes first" → WRONG. Create tasks for ALL items.
+- "This one was labeled 'long-term' by the team" → WRONG. Track it. The user decides when to execute, not you.
+- "I'll defer these as lower priority" → WRONG. You may SUGGEST a priority order, but every item must be a tracked task.
+- "The ready queue would be too large" → WRONG. A large queue is correct. A filtered queue is data loss.
+- "I already created the important ones" → WRONG. Important is not your call. Create ALL of them.
+
+**What you MAY do:**
+- Suggest a priority order (P0/P1/P2/P3) — but ALL items get tasks regardless of priority
+- Group related items into stories — but every item must appear as a criterion in at least one story
+- Ask the user to confirm scope — but do NOT preemptively filter
+
+**What you must NEVER do:**
+- Silently drop items because you judged them as "enhancements" or "nice-to-haves"
+- Create tasks for only a subset of items without explicit user approval to defer the rest
+- Use words like "deferred", "skipped", or "not created" for items the user provided
+
+**This rule applies everywhere**: `/wogi-start`, `/wogi-story`, `/wogi-epics`, `/wogi-extract-review`, and any other command that converts user input into tracked work.
+
 ### Task ID Format (MANDATORY)
 
 All task IDs MUST be generated by `generateTaskId()` from `wogiflow/scripts/flow-utils.js`. **Never manually type a task ID.**
@@ -282,7 +307,11 @@ Before closing any task, ensure all required gates pass (per `config.json → qu
 
 ## Context Management
 
-Context compaction happens automatically — WogiFlow persists all critical state to disk continuously, and the PostCompact hook restores it after compaction. You do NOT need to manually run `/wogi-pre-compact` before compaction.
+Context compaction happens **automatically and silently**. The user must NEVER be bothered with compaction. WogiFlow persists all critical state to disk continuously, and the PostCompact hook restores it after compaction.
+
+**NEVER invoke `/wogi-pre-compact` proactively.** Only run it when the user explicitly asks to compact or save context. When the user says "continue", "go ahead", or "keep going" — that means **start the next task**, not compact. Compaction is the SYSTEM's job, not yours.
+
+**Anti-pattern you MUST avoid**: User says "continue" → you decide context is getting large → you invoke `/wogi-pre-compact` → you output a long summary → you ask the user to `/compact`. This is WRONG. The user said "continue" — start the next task immediately.
 
 **What survives compaction automatically** (via PostCompact hook + state files):
 - Active task ID, title, type, and acceptance criteria
@@ -292,9 +321,13 @@ Context compaction happens automatically — WogiFlow persists all critical stat
 - Last request-log entry number
 - Routing enforcement (re-armed automatically)
 
-**`/wogi-pre-compact` is optional** — use it only when you want a detailed summary for a very long session. It is NOT required for state safety.
+**When auto-compaction triggers mid-session**: The system handles it. The PostCompact hook reloads state. You resume working on the next task from `ready.json`. No user interaction needed.
+
+**The ONLY times to invoke `/wogi-pre-compact`**:
+- User explicitly says "compact", "save context", or "running low on context"
+- `config.autoCompact.betweenTasks` is true AND you're between tasks AND context is above threshold — but even then, just compact silently and continue, don't ask
 
-**For L1+ tasks**: The pre-task context estimator (Step 0.25) checks if the task fits in remaining context. If it doesn't → compact BEFORE starting to avoid mid-task compaction.
+**For L1+ tasks**: The pre-task context estimator (Step 0.25) checks if the task fits in remaining context. If it doesn't → compact silently and continue, do NOT ask the user.
 
 ## Compact Instructions
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wogiflow",
-  "version": "2.3.0",
+  "version": "2.3.2",
   "description": "AI-powered development workflow management system with multi-model support",
   "main": "lib/index.js",
   "bin": {