specweave 1.0.151 → 1.0.152

package/CLAUDE.md

@@ -1,6 +1,6 @@
-<!-- SW:META template="claude" version="1.0.150" sections="header,start,autodetect,metarule,rules,workflow,reflect,context,structure,taskformat,secrets,syncing,testing,tdd,api,limits,troubleshooting,lazyloading,principles,linking,mcp,auto,docs" -->
+<!-- SW:META template="claude" version="1.0.151" sections="header,start,autodetect,metarule,rules,workflow,reflect,context,structure,taskformat,secrets,syncing,testing,tdd,api,limits,troubleshooting,lazyloading,principles,linking,mcp,auto,docs" -->
 
-<!-- SW:SECTION:header version="1.0.150" -->
+<!-- SW:SECTION:header version="1.0.151" -->
 **Framework**: SpecWeave | **Truth**: `spec.md` + `tasks.md`
 <!-- SW:END:header -->
 
@@ -58,7 +58,7 @@ plugins/specweave/
 **Old "commands" are just skills with `disable-model-invocation: true`** - they only respond to explicit `/name` invocation, not keyword detection.
 <!-- SW:END:claude-code-concepts -->
 
-<!-- SW:SECTION:start version="1.0.150" -->
+<!-- SW:SECTION:start version="1.0.151" -->
 ## Getting Started
 
 **Initial increment**: `0001-project-setup` (auto-created by `specweave init`)
@@ -68,7 +68,7 @@ plugins/specweave/
 2. **Customize**: Edit spec.md and use for setup tasks
 <!-- SW:END:start -->
 
-<!-- SW:SECTION:autodetect version="1.0.150" -->
+<!-- SW:SECTION:autodetect version="1.0.151" -->
 ## Auto-Detection
 
 SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
@@ -78,7 +78,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 **Opt-out phrases**: "Just brainstorm first" | "Don't plan yet" | "Quick discussion" | "Let's explore ideas"
 <!-- SW:END:autodetect -->
 
-<!-- SW:SECTION:metarule version="1.0.150" -->
+<!-- SW:SECTION:metarule version="1.0.151" -->
 ## Meta-Rule: Think-Before-Act
 
 **Satisfy dependencies BEFORE dependent operations.**
@@ -89,7 +89,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 ```
 <!-- SW:END:metarule -->
 
-<!-- SW:SECTION:rules version="1.0.150" -->
+<!-- SW:SECTION:rules version="1.0.151" -->
 ## Rules
 
 1. **Files** → `.specweave/increments/####-name/` (see Structure section for details)
@@ -100,7 +100,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 6. **⛔ Marketplace refresh**: Use `specweave refresh-marketplace` CLI (not `scripts/refresh-marketplace.sh`)
 <!-- SW:END:rules -->
 
-<!-- SW:SECTION:workflow version="1.0.150" -->
+<!-- SW:SECTION:workflow version="1.0.151" -->
 ## Workflow
 
 `/sw:increment "X"` → `/sw:do` → `/sw:progress` → `/sw:done 0001`
@@ -120,7 +120,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 **Natural language**: "Let's build X" → `/sw:increment` | "What's status?" → `/sw:progress` | "We're done" → `/sw:done` | "Ship while sleeping" → `/sw:auto`
 <!-- SW:END:workflow -->
 
-<!-- SW:SECTION:reflect version="1.0.150" -->
+<!-- SW:SECTION:reflect version="1.0.151" -->
 ## Skill Memories
 
 SpecWeave learns from corrections. Learnings saved here automatically. Edit or delete as needed.
@@ -133,7 +133,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 <!-- Auto-captured by SpecWeave reflect. Edit or delete as needed. -->
 <!-- Learnings are organized by skill name. User edits override SpecWeave defaults. -->
 
-<!-- SW:SECTION:context version="1.0.150" -->
+<!-- SW:SECTION:context version="1.0.151" -->
 ## Context
 
 **Before implementing**: Check ADRs at `.specweave/docs/internal/architecture/adr/`
@@ -141,7 +141,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 **Load context**: `/sw:context <topic>` loads relevant living docs into conversation
 <!-- SW:END:context -->
 
-<!-- SW:SECTION:structure version="1.0.150" -->
+<!-- SW:SECTION:structure version="1.0.151" -->
 ## Structure
 
 ```
@@ -156,7 +156,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 **Everything else → subfolders**: `reports/` | `logs/` | `scripts/` | `backups/`
 <!-- SW:END:structure -->
 
-<!-- SW:SECTION:taskformat version="1.0.150" -->
+<!-- SW:SECTION:taskformat version="1.0.151" -->
 ## Task Format
 
 ```markdown
@@ -166,7 +166,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 ```
 <!-- SW:END:taskformat -->
 
-<!-- SW:SECTION:secrets version="1.0.150" -->
+<!-- SW:SECTION:secrets version="1.0.151" -->
 ## Secrets Check
 
 **BEFORE CLI tools**: Check existing config first!
@@ -180,7 +180,7 @@ gh auth status
 **SECURITY**: NEVER use `grep TOKEN .env` without `-q` flag - it exposes credentials in terminal!
 <!-- SW:END:secrets -->
 
-<!-- SW:SECTION:syncing version="1.0.150" -->
+<!-- SW:SECTION:syncing version="1.0.151" -->
 ## External Sync (GitHub/JIRA/ADO)
 
 **Commands**: `/sw-github:sync {id}` (issues) | `/sw:sync-specs` (living docs only)
@@ -190,7 +190,7 @@ gh auth status
 **Config**: Set `sync.github.enabled: true` + `canUpdateExternalItems: true` in config.json
 <!-- SW:END:syncing -->
 
-<!-- SW:SECTION:testing version="1.0.150" -->
+<!-- SW:SECTION:testing version="1.0.151" -->
 ## Testing
 
 BDD in tasks.md | Unit >80% | `.test.ts` (Vitest)
@@ -202,7 +202,7 @@ vi.mock('./module', () => ({ func: mockFn }));
 ```
 <!-- SW:END:testing -->
 
-<!-- SW:SECTION:tdd version="1.0.150" -->
+<!-- SW:SECTION:tdd version="1.0.151" -->
 ## TDD Mode (Test-Driven Development)
 
 **When `testing.defaultTestMode: "TDD"` is configured**, follow RED-GREEN-REFACTOR discipline:
@@ -263,7 +263,7 @@ When TDD is enabled, tasks include phase markers:
 **Rule**: Complete dependencies BEFORE dependent tasks (RED before GREEN).
 <!-- SW:END:tdd -->
 
-<!-- SW:SECTION:api version="1.0.150" -->
+<!-- SW:SECTION:api version="1.0.151" -->
 ## API Development (OpenAPI-First)
 
 **For API projects only.** Commands: `/sw:api-docs --all` | `--openapi` | `--postman` | `--validate`
@@ -271,13 +271,13 @@ When TDD is enabled, tasks include phase markers:
 Enable in config: `{"apiDocs":{"enabled":true,"openApiPath":"openapi.yaml"}}`
 <!-- SW:END:api -->
 
-<!-- SW:SECTION:limits version="1.0.150" -->
+<!-- SW:SECTION:limits version="1.0.151" -->
 ## Limits
 
 **Max 1500 lines/file** — extract before adding
 <!-- SW:END:limits -->
 
-<!-- SW:SECTION:troubleshooting version="1.0.150" -->
+<!-- SW:SECTION:troubleshooting version="1.0.151" -->
 ## Troubleshooting
 
 | Issue | Fix |
@@ -293,7 +293,7 @@ Enable in config: `{"apiDocs":{"enabled":true,"openApiPath":"openapi.yaml"}}`
 | Marketplace shows 0 | Normal with auto-load; `/plugin list` shows actual |
 <!-- SW:END:troubleshooting -->
 
-<!-- SW:SECTION:lazyloading version="1.0.150" -->
+<!-- SW:SECTION:lazyloading version="1.0.151" -->
 ## Plugin Auto-Loading
 
 Plugins load automatically based on project type and keywords. Manual install if needed:
@@ -307,7 +307,7 @@ export SPECWEAVE_DISABLE_AUTO_LOAD=1         # Disable auto-load
 **Token savings**: Core ~3-5K tokens vs all plugins ~60K+
 <!-- SW:END:lazyloading -->
 
-<!-- SW:SECTION:principles version="1.0.150" -->
+<!-- SW:SECTION:principles version="1.0.151" -->
 ## Principles
 
 1. **Spec-first**: `/sw:increment` before coding
@@ -316,7 +316,7 @@ export SPECWEAVE_DISABLE_AUTO_LOAD=1         # Disable auto-load
 4. **Traceable**: All work → specs → ACs
 <!-- SW:END:principles -->
 
-<!-- SW:SECTION:linking version="1.0.150" -->
+<!-- SW:SECTION:linking version="1.0.151" -->
 ## Bidirectional Linking
 
 Tasks ↔ User Stories auto-linked via AC-IDs: `AC-US1-01` → `US-001`
@@ -324,7 +324,7 @@ Tasks ↔ User Stories auto-linked via AC-IDs: `AC-US1-01` → `US-001`
 Task format: `**AC**: AC-US1-01, AC-US1-02` (CRITICAL for linking)
 <!-- SW:END:linking -->
 
-<!-- SW:SECTION:mcp version="1.0.150" -->
+<!-- SW:SECTION:mcp version="1.0.151" -->
 ## External Services
 
 **Priority**: CLI tools first (simpler) → MCP for complex integrations
@@ -346,7 +346,7 @@ claude mcp add --transport stdio postgres -- npx -y @modelcontextprotocol/server
 MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
 <!-- SW:END:mcp -->
 
-<!-- SW:SECTION:auto version="1.0.150" -->
+<!-- SW:SECTION:auto version="1.0.151" -->
 ## Auto Mode
 
 **Commands**: `/sw:auto` (start) | `/sw:auto-status` (check) | `/sw:cancel-auto` (emergency only)
@@ -363,7 +363,7 @@ MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
 **STOP & ASK** if: Spec conflicts | Task unnecessary | Requirement ambiguous
 <!-- SW:END:auto -->
 
-<!-- SW:SECTION:docs version="1.0.150" -->
+<!-- SW:SECTION:docs version="1.0.151" -->
 ## Docs
 
 [spec-weave.com](https://spec-weave.com)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specweave",
-  "version": "1.0.151",
+  "version": "1.0.152",
   "description": "Spec-driven development framework for Claude Code. AI-native workflow with living documentation, intelligent agents, and multilingual support (9 languages). Enterprise-grade traceability with permanent specs and temporary increments.",
   "type": "module",
   "main": "dist/index.js",

package/plugins/specweave/hooks/universal/fail-fast-wrapper.sh

@@ -1,6 +1,7 @@
 #!/bin/bash
 # fail-fast-wrapper.sh - Non-blocking timeout wrapper for hooks
 #
+# v1.0.153: Hook-specific timeouts (user-prompt-submit: 30s for LLM detection)
 # v1.0.102+: Cross-platform support (Linux, macOS, BSD, Windows Git Bash)
 #
 # CRITICAL DESIGN PRINCIPLE:
@@ -20,7 +21,30 @@
 set +e  # CRITICAL: Never exit on error
 
 HOOK_TIMEOUT="${HOOK_TIMEOUT:-5}"
-WRAPPER_VERSION="1.0.102"
+WRAPPER_VERSION="1.0.153"
+
+# ============================================================================
+# HOOK-SPECIFIC TIMEOUT OVERRIDES (v1.0.153)
+# ============================================================================
+# Some hooks require longer timeouts due to LLM calls or network operations.
+# user-prompt-submit.sh: LLM-based detect-intent (~15s) + plugin installs (~4s)
+# Override defaults here while keeping fast timeouts for simple hooks.
+#
+# Environment overrides (if you need custom values):
+#   HOOK_TIMEOUT_USER_PROMPT - timeout for user-prompt-submit (default: 30)
+#   HOOK_TIMEOUT_SESSION_START - timeout for session-start (default: 20)
+
+script_name=$(basename "${1:-}" 2>/dev/null)
+case "$script_name" in
+  user-prompt-submit.sh)
+    # LLM-based plugin detection (~15s) + plugin installs (~4s) + buffer
+    HOOK_TIMEOUT="${HOOK_TIMEOUT_USER_PROMPT:-30}"
+    ;;
+  session-start.sh)
+    # Project detection may involve file scanning and optional LLM
+    HOOK_TIMEOUT="${HOOK_TIMEOUT_SESSION_START:-20}"
+    ;;
+esac
 
 # ============================================================================
 # PROJECT ROOT DETECTION (for logging) - CRITICAL: must NOT fallback to pwd!