release: v0.1.46 — 47 forcing questions, 12 execution fixes, deep review gates

Quality system:
- 47 forcing questions across 4 pipeline stages (brainstorm/plan_review/impl_review/close)
- Every question has reject/accept criteria + mandatory pushback
- Quantitative scoring gates at every stage (/25, /30, /30, /21)
- Adaptive tier sizing (Trivial 6Q, Medium 17Q, Large 20Q)

Execution fixes (12 issues resolved):
- P0: get_flow_dir walk-up (fixes state loss in subdirectories)
- P0: flowctl recover (rebuilds state from git history)
- P1: guard fallback + review-backend availability check
- P2: slug 20 chars, brainstorm auto-skip, --interactive flag

370 tests pass. Binary: flowctl 0.1.46.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: z23cc

.claude-plugin/marketplace.json

@@ -6,13 +6,13 @@
   },
   "metadata": {
     "description": "Structured plan-first development plugin for Claude Code with .flow/ task tracking, Agent Teams, and Ralph autonomous mode",
-    "version": "0.1.45"
+    "version": "0.1.46"
   },
   "plugins": [
     {
       "name": "flow-code",
       "description": "Zero-dependency planning + execution with .flow/ task tracking. Three-layer quality (guard + RP plan-review + Codex adversarial). Full-auto, zero questions. Teams auto-parallel, DAG mutation, Codex-driven decisions, auto draft-PR, session summary. 5 prompt templates. 24 subagents, 22 commands, 74 skills.",
-      "version": "0.1.45",
+      "version": "0.1.46",
       "source": "./",
       "category": "workflow",
       "tags": [
@@ -26,5 +26,5 @@
       "strict": true
     }
   ],
-  "version": "0.1.45"
+  "version": "0.1.46"
 }

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "flow-code",
-  "version": "0.1.45",
+  "version": "0.1.46",
   "description": "Zero-dependency planning + execution with .flow/ task tracking and Ralph autonomous mode (multi-model review gates). Worker subagent per task with git worktree isolation for parallel execution. Three-layer quality system (guard + RP plan-review + Codex adversarial). Full-auto by default — AI decides from context, zero questions. Teams-default with file locking, DAG mutation, Codex-driven conflict resolution, auto draft-PR. Auto-detected stack profiles with one-command guard (test/lint/typecheck). Enhanced agent definitions with permissionMode/maxTurns/effort. Lifecycle hooks with state preservation (PreCompact injects .flow state into compaction, TaskCompleted auto-unlocks files, SubagentStart context injection). Memory v2 with atomic entries, dedup, and progressive disclosure. TDD enforcement mode. Multi-epic queue with dependency visualization. Includes 24 subagents, 22 commands, 74 skills.",
   "author": {
     "name": "z23cc",

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "flow-code",
-  "version": "0.1.45",
+  "version": "0.1.46",
   "description": "Zero-dependency planning + execution with .flow/ task tracking and Ralph autonomous mode (multi-model review gates). Worker subagent per task with git worktree isolation for parallel execution. Three-layer quality system (guard + RP plan-review + Codex adversarial). Full-auto by default. Teams-default with file locking, DAG mutation, Codex-driven conflict resolution, auto draft-PR.",
   "author": {
     "name": "z23cc",

CHANGELOG.md

@@ -4,6 +4,27 @@ All notable changes to Flow-Code are documented in this file.
 
 Format follows [Keep a Changelog](https://keepachangelog.com/). Versions use [Semantic Versioning](https://semver.org/).
 
+## [0.1.46] - 2026-04-09
+
+### Added
+- **47 forcing questions** across entire pipeline (brainstorm 20Q + plan_review 10Q + impl_review 10Q + close 7Q)
+- Every question has reject/accept criteria + mandatory pushback
+- Quantitative scoring gates: brainstorm /25, plan_review /30, impl_review /30, close /21
+- Brainstorm 5 dimensions: Problem Reality, Solution Space, Risk & Failure, Implementation, Long-term
+- Plan review: Premise Challenge (4Q) + Architecture Interrogation (6Q)
+- Impl review: Correctness (5Q) + Quality (5Q) + 3-layer parallel review
+- Close: Ship-readiness interrogation with security grep, impact analysis, rollback plan
+- Adaptive tier sizing: Trivial 6Q, Medium 17Q, Large 20Q (brainstorm)
+
+### Fixed
+- **P0: State directory resolution** — `get_flow_dir()` now walks up directory tree (fixes state loss in subdirectories)
+- **P0: State recovery** — `flowctl recover --epic <id>` rebuilds task status from git history
+- **P1: Guard fallback** — missing tools → "skipped" not "failed" (doesn't block pipeline)
+- **P1: Review-backend verify** — rp-cli/codex not in PATH → auto-fallback to "none"
+- **P2: Slug length** — max 40 → 20 characters (shorter task IDs)
+- **P2: Brainstorm auto-skip** — trivial tasks (≤10 words, "fix"/"typo") skip brainstorm
+- **P2: --interactive flag** — pause at key decisions for user confirmation
+
 ## [0.1.45] - 2026-04-09
 
 ### Added

README.md

@@ -6,7 +6,7 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](../../LICENSE)
 [![Claude Code](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet)](https://claude.ai/code)
-[![Version](https://img.shields.io/badge/Version-0.1.45-green)](https://github.com/z23cc/flow-code/releases)
+[![Version](https://img.shields.io/badge/Version-0.1.46-green)](https://github.com/z23cc/flow-code/releases)
 
 **A production-grade harness for Claude Code. Full-auto development from idea to PR.**
 

README_CN.md

@@ -6,7 +6,7 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](../../LICENSE)
 [![Claude Code](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet)](https://claude.ai/code)
-[![Version](https://img.shields.io/badge/Version-0.1.45-green)](https://github.com/z23cc/flow-code/releases)
+[![Version](https://img.shields.io/badge/Version-0.1.46-green)](https://github.com/z23cc/flow-code/releases)
 
 **Claude Code 的生产级开发框架。从想法到 PR，全自动。**
 

bin/flowctl

@@ -1,6 +1,6 @@
 [package]
 name = "flowctl-cli"
-version = "0.1.45"
+version = "0.1.46"
 description = "CLI entry point for flowctl"
 edition.workspace = true
 rust-version.workspace = true