@the-bearded-bear/claude-craft 8.26.0 → 8.27.0

package/README.md

@@ -26,7 +26,11 @@ Plus **11 stack-specific reviewers** (@symfony-reviewer, @react-reviewer, @pytho
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Mutation testing badge](https://img.shields.io/endpoint?style=flat&url=https%3A%2F%2Fbadge-api.stryker-mutator.io%2Fgithub.com%2FTheBeardedBearSAS%2Fclaude-craft%2Fmain)](https://dashboard.stryker-mutator.io/reports/github.com/TheBeardedBearSAS/claude-craft/main)
 
-A comprehensive framework for AI-assisted development with [Claude Code](https://claude.ai/code). Install standardized rules, agents, and commands for your projects across multiple technology stacks — **33 specialized agents (+39 infra agents on-demand), 139 commands across 17 namespaces (238 total, including deprecated redirect stubs kept until 9.0), 55 skills**, all token-optimized via `context: fork` and sub-agent model routing.
+A comprehensive framework for AI-assisted development with [Claude Code](https://claude.ai/code). Install standardized rules, agents, and commands for your projects across multiple technology stacks — **33 specialized agents (+39 infra agents on-demand), 140 commands across 18 namespaces (238 total, including deprecated redirect stubs kept until 9.0), 55 skills**, all token-optimized via `context: fork` and sub-agent model routing.
+
+## What's New in v8.27.0
+
+**Les commandes `/team:*` sans Agent Teams (2026-10-28, v8.27.0) :** `/team:audit`, `/team:security`, `/team:sprint` et `/team:delivery` délèguent par défaut à des sous-agents (`--engine=subagents`, compatible `claude -p` et CI) ; Agent Teams devient optionnel (`--engine=teams`, repli automatique si `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` est absent). `/common:research-context7` et `/uiux:orchestrator` sont dépréciées au profit du MCP context7 / `/deep-research` et de l'agent `@uiux-orchestrator`. Ralph est fiabilisé en mode parallèle (sessions et worktrees isolés). Claude Code recommandé : 2.1.312. Dernière version 8.x avant la 9.0. Détails : [CHANGELOG](CHANGELOG.md#8270---2026-10-28).
 
 ## What's New in v8.26.0
 
@@ -69,7 +73,7 @@ A comprehensive framework for AI-assisted development with [Claude Code](https:/
 
 - **Sécurité** : classement OWASP Top 10:2025 officiel (A01–A10) dans la règle 11 et ses miroirs, avec test de régression ; FrankenPHP 1.13.0 et PgBouncer 1.26.0 (versions précédentes vulnérables) ; types de serveurs Hetzner et `datacenter` retirés corrigés.
 - **Versions vérifiées sur registres** : React 19.3, Flutter 3.47, React Native 0.87 / Expo 57, Pinia 4, Vite 8.3 (`rolldownOptions`), Vercel CLI 63, Python 3.15, Paperclip 2026.1012.0, Docker 29.9, Kubernetes 1.37 (Gateway API), Vitest 5, Pest 5, pytest 9, PER-CS 3.0.
-- **Claude Code** : minimum 2.1.260, recommandé 2.1.296, modèles 5.5. Détails : [CHANGELOG](CHANGELOG.md#8230---2026-10-13).
+- **Claude Code** : minimum 2.1.260, recommandé 2.1.312, modèles 5.5. Détails : [CHANGELOG](CHANGELOG.md#8230---2026-10-13).
 
 ## What's New in v8.18.0
 
@@ -147,8 +151,8 @@ A comprehensive framework for AI-assisted development with [Claude Code](https:/
 - **MIT-only strict (v8.8.0)** -- Claude Craft est 100 % open-source MIT, aucune licence commerciale ou enterprise. Stratégie open-core abandonnée.
 - **Parité i18n stricte (v8.8.2)** -- la CI bloque désormais si un fichier traduit est à < 80 % de la taille de l'anglais. Dette i18n résorbée (gap 101 → 0).
 - **Branding the-bearded-bear.com (v8.10.1)** -- migration complète des domaines vers `the-bearded-bear.com`, normalisation de l'organisation GitHub.
-- **126 commandes sur 15 namespaces** (220 total avec infra/projet) -- namespace `/paperclip:*` (8 commandes) ajouté, 55 skills disponibles.
-- **Claude Code 2.1.296** -- version recommandée (minimum sécurité 2.1.260 ; Opus 5.5 / Sonnet 5.5 / Haiku 5.5, MCP 2026-07-28, hooks `onFailure: "block"`).
+- **126 commandes sur 15 namespaces (v8.10.x)** (220 total avec infra/projet) -- namespace `/paperclip:*` (8 commandes) ajouté, 55 skills disponibles.
+- **Claude Code 2.1.312** -- version recommandée (minimum sécurité 2.1.260 ; Opus 5.5 / Sonnet 5.5 / Haiku 5.5, MCP 2026-07-28, hooks `onFailure: "block"`).
 
 > ← Versions antérieures (v8.0 → v8.7) : voir le [CHANGELOG](CHANGELOG.md) et [.claude/COMPATIBILITY.md](.claude/COMPATIBILITY.md).
 
@@ -187,7 +191,7 @@ Claude Code is powerful on its own. Claude Craft makes it **consistent and team-
 
 - **Standardized rules** -- SOLID, Clean Architecture, TDD enforced across your team, not just suggested
 - **33 default agents + 39 infra agents on-demand** -- reviewers, architects, coaches that know your stack deeply (72 total potentially installable)
-- **139 slash commands across 17 namespaces** -- repeatable workflows for audits, code generation, sprint management
+- **140 slash commands across 18 namespaces** -- repeatable workflows for audits, code generation, sprint management
 - **Quality gates** -- automated checks at every stage from PRD to deployment
 - **5 languages** -- English, French, Spanish, German, Portuguese
 
@@ -225,7 +229,7 @@ See [Technologies](docs/TECHNOLOGIES.md) for full details.
 | Category | Count | Examples |
 |----------|-------|---------|
 | **Agents** | 31 default (+ 39 infra on-demand) | `@tdd-coach`, `@api-designer`, `@symfony-reviewer`, `@kubernetes-architect`, `@hcloud-architect` |
-| **Commands** | 126 across 15 namespaces (220 total with infra/project) | `/workflow:init`, `/team:audit`, `/react:generate-component` |
+| **Commands** | 140 across 18 namespaces (238 total with infra/project) | `/workflow:init`, `/team:audit`, `/react:generate-component` |
 | **Skills** | 55 | Architecture, testing, security, DDD best practices |
 | **Templates** | 21 | Code generation patterns, BMAD project templates |
 | **Checklists** | 10 | Commit, feature, release quality gates |
@@ -267,7 +271,7 @@ These are the commands you'll use most:
 | `/common:ralph-run "task"` | Run Claude in continuous loop until task is done |
 | `/qa:recette` | Automated acceptance testing via Chrome |
 
-See [CLI Reference](docs/CLI-REFERENCE.md) for all 126 commands across 15 core namespaces (220 total including infra and project management).
+See [CLI Reference](docs/CLI-REFERENCE.md) for all 140 commands across 18 namespaces (238 total including infra, project management and deprecated redirect stubs kept until 9.0).
 
 ## Installation
 
@@ -350,7 +354,7 @@ Context usage is optimized: ~3,500 tokens always loaded vs ~70,000 if everything
 | [Installation](docs/INSTALLATION.md) | All installation methods |
 | [Configuration](docs/CONFIGURATION.md) | Project configuration |
 | [CLI Reference](docs/CLI-REFERENCE.md) | Full CLI documentation |
-| [Commands](docs/COMMANDS.md) | All 126 commands |
+| [Commands](docs/COMMANDS.md) | All 140 commands |
 | [Agents](docs/AGENTS.md) | All 31 default agents (+ 39 infra on-demand) |
 | [Skills](docs/SKILLS.md) | Best practices reference |
 | [Technologies](docs/TECHNOLOGIES.md) | Stack-specific guides |

package/Tools/Ralph/lib/checkpoint.sh

@@ -207,12 +207,12 @@ list_checkpoints() {
 
     # Find commits matching the checkpoint pattern
     local commits
-    commits=$(git log --oneline --grep="checkpoint: Ralph" 2>/dev/null | head -20)
+    commits=$(git log --oneline --grep="checkpoint: Ralph" 2>/dev/null | head -20) || true
 
     if [[ -n "$commits" ]]; then
         echo "$commits" | while read -r line; do
-            local hash=$(echo "$line" | cut -d' ' -f1)
-            local msg=$(echo "$line" | cut -d' ' -f2-)
+            local hash=$(echo "$line" | cut -d' ' -f1) || true
+            local msg=$(echo "$line" | cut -d' ' -f2-) || true
             echo "{\"hash\":\"$hash\",\"message\":\"$msg\"}"
         done | jq -s '.'
     else

package/Tools/Ralph/lib/circuit-breaker.sh

@@ -30,35 +30,35 @@ CB_LEARNING_MIN_SAMPLES=5
 # =============================================================================
 # Each profile defines thresholds optimized for different task types
 
-declare -A CB_PROFILE_QUICK_FIX=(
+declare -gA CB_PROFILE_QUICK_FIX=(
     ["no_changes"]=2
     ["errors"]=3
     ["max_iterations"]=10
     ["keywords"]="fix bug typo hotfix patch"
 )
 
-declare -A CB_PROFILE_SMALL_FEATURE=(
+declare -gA CB_PROFILE_SMALL_FEATURE=(
     ["no_changes"]=3
     ["errors"]=4
     ["max_iterations"]=15
     ["keywords"]="add implement small simple"
 )
 
-declare -A CB_PROFILE_MEDIUM_FEATURE=(
+declare -gA CB_PROFILE_MEDIUM_FEATURE=(
     ["no_changes"]=4
     ["errors"]=6
     ["max_iterations"]=25
     ["keywords"]="feature create with tests"
 )
 
-declare -A CB_PROFILE_LARGE_FEATURE=(
+declare -gA CB_PROFILE_LARGE_FEATURE=(
     ["no_changes"]=5
     ["errors"]=8
     ["max_iterations"]=50
     ["keywords"]="refactor migrate complex large"
 )
 
-declare -A CB_PROFILE_EXPLORATION=(
+declare -gA CB_PROFILE_EXPLORATION=(
     ["no_changes"]=10
     ["errors"]=15
     ["max_iterations"]=100
@@ -66,7 +66,7 @@ declare -A CB_PROFILE_EXPLORATION=(
 )
 
 # Autonomous profile for overnight/unattended runs
-declare -A CB_PROFILE_AUTONOMOUS=(
+declare -gA CB_PROFILE_AUTONOMOUS=(
     ["no_changes"]=5
     ["errors"]=8
     ["max_iterations"]=50
@@ -162,7 +162,7 @@ init_circuit_breaker() {
 detect_task_profile() {
     local prompt="$1"
     local prompt_lower
-    prompt_lower=$(echo "$prompt" | tr '[:upper:]' '[:lower:]')
+    prompt_lower=$(echo "$prompt" | tr '[:upper:]' '[:lower:]') || true
 
     # Check each profile's keywords
     local profiles=("quick_fix" "small_feature" "medium_feature" "large_feature" "exploration" "autonomous")
@@ -265,7 +265,7 @@ apply_learned_adjustments() {
     ' "$history_file" 2>/dev/null)
 
     local samples
-    samples=$(echo "$profile_data" | jq -r '.samples // 0')
+    samples=$(echo "$profile_data" | jq -r '.samples // 0') || samples=0
 
     if [[ $samples -lt $CB_LEARNING_MIN_SAMPLES ]]; then
         print_verbose "Not enough samples for learning ($samples < $CB_LEARNING_MIN_SAMPLES)"
@@ -274,10 +274,10 @@ apply_learned_adjustments() {
 
     # Apply adjustments based on historical success rate
     local success_rate
-    success_rate=$(echo "$profile_data" | jq -r '.success_rate // 0')
+    success_rate=$(echo "$profile_data" | jq -r '.success_rate // 0') || success_rate=0
 
     local avg_iterations
-    avg_iterations=$(echo "$profile_data" | jq -r '.avg_iterations // 0')
+    avg_iterations=$(echo "$profile_data" | jq -r '.avg_iterations // 0') || avg_iterations=0
 
     # If success rate is low, increase thresholds
     if [[ $success_rate -lt 50 ]]; then

package/Tools/Ralph/lib/context-manager.sh

@@ -32,6 +32,9 @@ IFS=' ' read -r -a CLAUDE_CMD <<< "$CLAUDE_COMMAND"
 CONTEXT_COMPACT_COUNT=0
 CONTEXT_CONTINUATION_COUNT=0
 CONTEXT_CONTINUATION_PROMPT=""
+# Set by run_auto_compact (return 3) / handle_max_compacts_reached: call them
+# in this shell, never in `$(...)`, or the counters above are lost.
+CONTEXT_NEW_SESSION_ID=""
 
 # =============================================================================
 # Context Limit Detection
@@ -106,6 +109,17 @@ init_context_manager() {
     print_verbose "  - Smart reconstruction: $CONTEXT_SMART_RECONSTRUCTION"
 }
 
+# Print the first lines of `/context` for a Claude session UUID.
+# Best effort: prints nothing on failure, always succeeds (set -e safe).
+probe_context_usage() {
+    local claude_uuid="$1"
+    if command -v timeout &> /dev/null; then
+        timeout 10s "${CLAUDE_CMD[@]}" --resume "$claude_uuid" -p "/context" 2>/dev/null | head -5 || true
+    else
+        "${CLAUDE_CMD[@]}" --resume "$claude_uuid" -p "/context" 2>/dev/null | head -5 || true
+    fi
+}
+
 # =============================================================================
 # Auto-Compact
 # =============================================================================
@@ -120,20 +134,27 @@ run_auto_compact() {
         return 1
     fi
 
+    # /context and /compact must target this Ralph session's Claude session,
+    # never "the most recent conversation in this directory" (--continue).
+    local claude_uuid
+    claude_uuid=$(get_claude_session_uuid "$session_id")
+    if [[ -z "$claude_uuid" ]]; then
+        log_session "$session_id" "WARN" "No Claude session yet, nothing to compact"
+        return 1
+    fi
+
     # Check if context is above minimum threshold before compacting
     if [[ "$CONTEXT_MIN_THRESHOLD" -gt 0 ]]; then
         local context_info
-        if command -v timeout &> /dev/null; then
-            context_info=$(timeout 10s "${CLAUDE_CMD[@]}" -p "/context" 2>/dev/null | head -5)
-        else
-            context_info=$("${CLAUDE_CMD[@]}" -p "/context" 2>/dev/null | head -5)
-        fi
+        context_info=$(probe_context_usage "$claude_uuid")
         local current_usage
-        current_usage=$(echo "$context_info" | grep -oP '\d+(?=%)' | head -1)
+        current_usage=$(echo "$context_info" | grep -oP '\d+(?=%)' | head -1 || true)
 
         if [[ -n "$current_usage" && "$current_usage" -lt "$CONTEXT_MIN_THRESHOLD" ]]; then
             log_session "$session_id" "INFO" "Context at ${current_usage}% - below minimum threshold (${CONTEXT_MIN_THRESHOLD}%), skipping compact"
-            print_verbose "Context at ${current_usage}% - below min threshold (${CONTEXT_MIN_THRESHOLD}%), skipping compact"
+            local msg="${MSG_CONTEXT_BELOW_MIN:-"Context at {0}% - below minimum threshold ({1}%), skipping compact"}"
+            msg="${msg//\{0\}/"$current_usage"}"
+            print_verbose "${msg//\{1\}/"$CONTEXT_MIN_THRESHOLD"}"
             return 1
         fi
     fi
@@ -144,13 +165,12 @@ run_auto_compact() {
         print_warning "${MSG_CONTEXT_MAX_REACHED:-Maximum compacts reached} ($CONTEXT_MAX_COMPACTS)"
 
         # Handle overflow strategy
-        local overflow_result
-        overflow_result=$(handle_max_compacts_reached "$session_id")
-        local overflow_status=$?
+        local overflow_status=0
+        CONTEXT_NEW_SESSION_ID=""
+        handle_max_compacts_reached "$session_id" || overflow_status=$?
 
-        if [[ $overflow_status -eq 0 && -n "$overflow_result" ]]; then
-            # New session ID returned - signal continuation
-            echo "$overflow_result"
+        if [[ $overflow_status -eq 0 && -n "$CONTEXT_NEW_SESSION_ID" ]]; then
+            # New session ID in CONTEXT_NEW_SESSION_ID - signal continuation
             return 3  # Special return code for session continuation
         fi
 
@@ -185,11 +205,10 @@ run_auto_compact() {
 
     # Execute /compact via Claude CLI
     local compact_output
-    local compact_status
+    local compact_status=0
 
     if command -v timeout &> /dev/null; then
-        compact_output=$(timeout 60s "${CLAUDE_CMD[@]}" --continue -p "/compact" 2>&1)
-        compact_status=$?
+        compact_output=$(timeout 60s "${CLAUDE_CMD[@]}" --resume "$claude_uuid" -p "/compact" 2>&1) || compact_status=$?
 
         # Handle timeout specifically (exit code 124)
         if [[ $compact_status -eq 124 ]]; then
@@ -198,8 +217,7 @@ run_auto_compact() {
             return 1
         fi
     else
-        compact_output=$("${CLAUDE_CMD[@]}" --continue -p "/compact" 2>&1)
-        compact_status=$?
+        compact_output=$("${CLAUDE_CMD[@]}" --resume "$claude_uuid" -p "/compact" 2>&1) || compact_status=$?
     fi
 
     if [[ $compact_status -eq 0 ]]; then
@@ -313,10 +331,12 @@ handle_max_compacts_reached() {
             new_session_id=$(create_continuation_session "$session_id")
 
             if [[ -n "$new_session_id" ]]; then
+                # Reset here: create_continuation_session ran in a subshell
+                CONTEXT_COMPACT_COUNT=0
                 CONTEXT_CONTINUATION_COUNT=$((CONTEXT_CONTINUATION_COUNT + 1))
                 print_success "${MSG_CONTEXT_CONTINUATION_CREATED:-Continuation session created}: $new_session_id"
                 log_session "$session_id" "INFO" "Created continuation session: $new_session_id"
-                echo "$new_session_id"
+                CONTEXT_NEW_SESSION_ID="$new_session_id"
                 return 0
             else
                 print_error "Failed to create continuation session"
@@ -349,30 +369,11 @@ handle_max_compacts_reached() {
 create_continuation_session() {
     local previous_session="$1"
 
-    # Generate new session ID with portable random suffix generation
-    local timestamp=$(date +%Y%m%d_%H%M%S)
-    local random_suffix
-
-    # Use utils function if available, otherwise fallback
-    if type generate_random_suffix &>/dev/null; then
-        random_suffix=$(generate_random_suffix 4)
-    elif command -v xxd &>/dev/null; then
-        random_suffix=$(head -c 4 /dev/urandom | xxd -p)
-    elif command -v od &>/dev/null; then
-        random_suffix=$(head -c 4 /dev/urandom | od -An -tx1 | tr -d ' \n')
-    else
-        # Fallback: use $RANDOM (less entropy but portable)
-        random_suffix=$(printf '%04x%04x' $RANDOM $RANDOM | head -c 8)
-    fi
-
-    local new_session_id="ralph-cont-${timestamp}-${random_suffix}"
-
-    # Create session directory if create_session is available
-    if type create_session &>/dev/null; then
-        if ! create_session "$new_session_id" 2>/dev/null; then
-            print_warning "Failed to create session directory for $new_session_id"
-        fi
-    fi
+    # create_session takes a prompt and prints the id it created (with its
+    # state.json and session.log): the id must come from it, or the session
+    # directory is an orphan and the continuation id has no state.
+    local new_session_id
+    new_session_id=$(create_session "Continuation of $previous_session") || return 1
 
     # Link sessions in state files (with error handling)
     if type update_session_state &>/dev/null; then
@@ -385,10 +386,6 @@ create_continuation_session() {
         link_session_to_progress "$new_session_id" || print_verbose "Failed to link session to progress"
     fi
 
-    # Reset context manager for new session
-    CONTEXT_COMPACT_COUNT=0
-    CONTEXT_CONTINUATION_COUNT=$((CONTEXT_CONTINUATION_COUNT))  # Keep continuation count
-
     echo "$new_session_id"
 }
 
@@ -404,26 +401,28 @@ check_preventive_compact() {
         return 1
     fi
 
+    # Nothing to measure before the first Claude call of this session.
+    local claude_uuid
+    claude_uuid=$(get_claude_session_uuid "$session_id")
+    [[ -z "$claude_uuid" ]] && return 1
+
     # Try to get context usage from Claude CLI
     # Note: This is a best-effort check, Claude may not always report usage
     local context_info
-    if command -v timeout &> /dev/null; then
-        context_info=$(timeout 10s "${CLAUDE_CMD[@]}" -p "/context" 2>/dev/null | head -5)
-    else
-        context_info=$("${CLAUDE_CMD[@]}" -p "/context" 2>/dev/null | head -5)
-    fi
+    context_info=$(probe_context_usage "$claude_uuid")
 
     # Try to extract percentage from output
     local usage
-    usage=$(echo "$context_info" | grep -oP '\d+(?=%)' | head -1)
+    usage=$(echo "$context_info" | grep -oP '\d+(?=%)' | head -1 || true)
 
     if [[ -n "$usage" && "$usage" -ge "$CONTEXT_PREVENTIVE_THRESHOLD" ]]; then
-        print_warning "${MSG_CONTEXT_PREVENTIVE:-Context at ${usage}% - running preventive compact}"
+        local msg="${MSG_CONTEXT_PREVENTIVE:-Context at ${usage}% - running preventive compact}"
+        print_warning "${msg//\{0\}/$usage}"
         log_session "$session_id" "INFO" "Preventive compact triggered at ${usage}%"
 
         # Save progress before preventive compact
         if type save_sprint_progress &>/dev/null; then
-            save_sprint_progress "$session_id"
+            save_sprint_progress "$session_id" || print_verbose "No sprint progress file to save"
         fi
 
         run_auto_compact "$session_id"
@@ -437,23 +436,15 @@ check_preventive_compact() {
 # Context Continuation Prompt
 # =============================================================================
 
+# Print the continuation prompt stored by a real compaction, if any.
+# Callers using `$(...)` must reset CONTEXT_CONTINUATION_PROMPT themselves.
 get_context_continuation_prompt() {
-    # Return the stored continuation prompt if available
     if [[ -n "$CONTEXT_CONTINUATION_PROMPT" ]]; then
         echo "$CONTEXT_CONTINUATION_PROMPT"
-        # Clear after use
         CONTEXT_CONTINUATION_PROMPT=""
         return 0
     fi
 
-    # Generate fresh if smart reconstruction is enabled
-    if [[ "$CONTEXT_SMART_RECONSTRUCTION" == "true" ]]; then
-        if type generate_continuation_prompt &>/dev/null; then
-            generate_continuation_prompt
-            return 0
-        fi
-    fi
-
     return 1
 }
 

package/Tools/Ralph/lib/context-reconstruction.sh

@@ -56,71 +56,75 @@ reconstruct_context() {
 # Section Builders
 # =============================================================================
 
+# Headings and sentences come from Tools/i18n/ralph/<lang>.sh (MSG_SECTION_*):
+# these sections are sent to Claude and must follow --lang.
+
 build_progress_section() {
-    echo "## Sprint Progress"
+    echo "${MSG_SECTION_PROGRESS:-## Sprint Progress}"
     echo ""
 
     if [[ -f "$SPRINT_PROGRESS_FILE" ]]; then
         # Extract key sections only (not the entire file)
-        echo "### Current State"
-        grep -A4 "^## Current State" "$SPRINT_PROGRESS_FILE" 2>/dev/null | tail -n +2 || echo "- Unknown"
+        echo "${MSG_SECTION_CURRENT_STATE:-### Current State}"
+        grep -A4 "^## Current State" "$SPRINT_PROGRESS_FILE" 2>/dev/null | tail -n +2 || echo "- ${MSG_SECTION_UNKNOWN:-Unknown}"
 
         echo ""
-        echo "### Completed Tasks"
+        echo "${MSG_SECTION_COMPLETED_TASKS:-### Completed Tasks}"
         # Show last 5 completed tasks
-        grep '^\- \[x\]' "$SPRINT_PROGRESS_FILE" 2>/dev/null | tail -5 || echo "- None yet"
+        grep '^\- \[x\]' "$SPRINT_PROGRESS_FILE" 2>/dev/null | tail -5 || echo "- ${MSG_SECTION_NONE_YET:-None yet}"
 
         echo ""
-        echo "### Key Decisions"
-        grep -A10 "^## Key Decisions" "$SPRINT_PROGRESS_FILE" 2>/dev/null | grep '^-' | head -5 || echo "- None recorded"
+        echo "${MSG_SECTION_KEY_DECISIONS:-### Key Decisions}"
+        grep -A10 "^## Key Decisions" "$SPRINT_PROGRESS_FILE" 2>/dev/null | grep '^-' | head -5 || echo "- ${MSG_SECTION_NONE_RECORDED:-None recorded}"
     else
-        echo "No sprint progress file found."
+        echo "${MSG_SECTION_NO_PROGRESS_FILE:-No sprint progress file found.}"
     fi
 }
 
 build_git_section() {
-    echo "## Recent Changes"
+    echo "${MSG_SECTION_GIT:-## Recent Changes}"
     echo ""
 
     # Check if we're in a git repository
     if ! git rev-parse --git-dir > /dev/null 2>&1; then
-        echo "Not in a git repository."
+        echo "${MSG_SECTION_NOT_GIT:-Not in a git repository.}"
         return
     fi
 
     # Get summary of changes - check commit count first
-    echo "### Modified Files (recent commits)"
+    echo "${MSG_SECTION_MODIFIED_FILES:-### Modified Files (recent commits)}"
     local commit_count
     commit_count=$(git rev-list --count HEAD 2>/dev/null || echo "0")
 
+    local no_changes="${MSG_SECTION_NO_RECENT_CHANGES:-No recent changes}"
     if [[ "$commit_count" -ge 5 ]]; then
-        git diff --stat HEAD~5 2>/dev/null | tail -15 || echo "No recent changes"
+        git diff --stat HEAD~5 2>/dev/null | tail -15 || echo "$no_changes"
     elif [[ "$commit_count" -gt 0 ]]; then
         # Show diff from initial commit if less than 5 commits
-        git diff --stat "$(git rev-list --max-parents=0 HEAD 2>/dev/null)" 2>/dev/null | tail -15 || echo "No recent changes"
+        git diff --stat "$(git rev-list --max-parents=0 HEAD 2>/dev/null)" 2>/dev/null | tail -15 || echo "$no_changes"
     else
-        echo "No commits yet"
+        echo "${MSG_SECTION_NO_COMMITS:-No commits yet}"
     fi
 
     echo ""
-    echo "### Recent Commits"
-    git log --oneline -5 2>/dev/null || echo "No commits found"
+    echo "${MSG_SECTION_RECENT_COMMITS:-### Recent Commits}"
+    git log --oneline -5 2>/dev/null || echo "${MSG_SECTION_NO_COMMITS:-No commits yet}"
 
     echo ""
-    echo "### Uncommitted Changes"
+    echo "${MSG_SECTION_UNCOMMITTED:-### Uncommitted Changes}"
     local status
-    status=$(git status --porcelain 2>/dev/null | head -10)
+    status=$(git status --porcelain 2>/dev/null | head -10) || true
     if [[ -n "$status" ]]; then
         echo "\`\`\`"
         echo "$status"
         echo "\`\`\`"
     else
-        echo "No uncommitted changes."
+        echo "${MSG_SECTION_NO_UNCOMMITTED:-No uncommitted changes.}"
     fi
 }
 
 build_test_section() {
-    echo "## Test Status"
+    echo "${MSG_SECTION_TESTS:-## Test Status}"
     echo ""
 
     # Try to detect test framework
@@ -149,7 +153,7 @@ build_test_section() {
     fi
 
     if [[ "$framework_detected" == "false" ]]; then
-        echo "- Framework: Unknown"
+        echo "- Framework: ${MSG_SECTION_UNKNOWN:-Unknown}"
     fi
 
     # Check sprint progress for recorded test status
@@ -158,13 +162,13 @@ build_test_section() {
         unit_status=$(grep -oP 'Unit: \K.*' "$SPRINT_PROGRESS_FILE" 2>/dev/null || echo "unknown")
         local integration_status
         integration_status=$(grep -oP 'Integration: \K.*' "$SPRINT_PROGRESS_FILE" 2>/dev/null || echo "unknown")
-        echo "- Unit Tests: $unit_status"
-        echo "- Integration Tests: $integration_status"
+        echo "- ${MSG_SECTION_UNIT_TESTS:-Unit Tests}: $unit_status"
+        echo "- ${MSG_SECTION_INTEGRATION_TESTS:-Integration Tests}: $integration_status"
     fi
 }
 
 build_current_task_section() {
-    echo "## Current Task"
+    echo "${MSG_SECTION_TASK:-## Current Task}"
     echo ""
 
     # Check for current task file
@@ -179,15 +183,16 @@ build_current_task_section() {
         local phase=$(grep -oP '\*\*Phase\*\*: \K.*' "$SPRINT_PROGRESS_FILE" 2>/dev/null)
 
         if [[ -n "$current_task" && "$current_task" != "none" ]]; then
-            echo "**Task**: $current_task"
-            echo "**Phase**: ${phase:-unknown}"
+            echo "**${MSG_SECTION_TASK_LABEL:-Task}**: $current_task"
+            echo "**${MSG_SPRINT_PHASE:-Phase}**: ${phase:-unknown}"
             echo ""
-            echo "Continue from where you left off in the $phase phase."
+            local msg="${MSG_SECTION_CONTINUE_PHASE:-"Continue from where you left off in the {0} phase."}"
+            echo "${msg//\{0\}/"$phase"}"
         else
-            echo "No current task in progress."
+            echo "${MSG_SECTION_NO_TASK:-No current task in progress.}"
         fi
     else
-        echo "No current task information available."
+        echo "${MSG_SECTION_NO_TASK_INFO:-No current task information available.}"
     fi
 }
 
@@ -195,34 +200,16 @@ build_current_task_section() {
 # Continuation Prompt Generation
 # =============================================================================
 
+# Templates come from Tools/i18n/ralph/<lang>.sh (MSG_PROMPT_*), so the
+# prompt sent to Claude follows --lang. Replacements are quoted: bash 5.2
+# would otherwise expand `&` in the context to the matched placeholder.
 generate_continuation_prompt() {
     local session_id="${SESSION_ID:-unknown}"
-    local context=$(reconstruct_context "$session_id")
-
-    cat << EOF
-# Continuation du Sprint
-
-Vous reprenez le travail sur ce sprint apres une compaction de contexte.
-Le fichier sprint-progress.md contient l'etat complet du travail effectue.
-
-$context
+    local context
+    context=$(reconstruct_context "$session_id")
 
-## Instructions
-
-1. **Lisez** le progres ci-dessus pour comprendre l'etat actuel
-2. **Verifiez** les fichiers modifies si necessaire
-3. **Reprenez** la tache en cours la ou elle s'est arretee
-4. **Continuez** le workflow TDD (RED -> GREEN -> REFACTOR)
-5. **Mettez a jour** sprint-progress.md apres chaque tache terminee
-
-## Commandes Importantes
-
-- Apres chaque tache: mettre a jour sprint-progress.md
-- Si blocker: noter dans la section Blockers
-- Si decision importante: ajouter dans Key Decisions
-
-Continuez l'implementation.
-EOF
+    local prompt="${MSG_PROMPT_CONTINUATION:-"{0}"}"
+    echo "${prompt//\{0\}/"$context"}"
 }
 
 # =============================================================================
@@ -231,32 +218,12 @@ EOF
 
 generate_session_handoff_prompt() {
     local previous_session="$1"
-    local context=$(reconstruct_context "$previous_session")
+    local context
+    context=$(reconstruct_context "$previous_session")
 
-    cat << EOF
-# Nouvelle Session de Continuation
-
-Cette session continue le travail de la session precedente ($previous_session).
-Le contexte a ete reinitialise mais le fichier sprint-progress.md contient tout le progres.
-
-$context
-
-## Contexte de la Transition
-
-- Session precedente: $previous_session
-- Raison: Limite de contexte atteinte (max compacts)
-- Le travail a ete sauvegarde dans sprint-progress.md
-- Les fichiers sont dans l'etat du dernier checkpoint git
-
-## Instructions
-
-1. **Verifiez** l'etat actuel via git status
-2. **Lisez** sprint-progress.md pour le contexte complet
-3. **Identifiez** la tache en cours et son etat
-4. **Continuez** exactement ou la session precedente s'est arretee
-
-Reprenez le travail.
-EOF
+    local prompt="${MSG_PROMPT_HANDOFF:-"{1}"}"
+    prompt="${prompt//\{0\}/"$previous_session"}"
+    echo "${prompt//\{1\}/"$context"}"
 }
 
 # =============================================================================

package/Tools/Ralph/lib/dod-templates.sh

@@ -18,7 +18,7 @@ get_dod_template() {
 
     # Normalize project type (remove version suffixes)
     local base_type
-    base_type=$(echo "$project_type" | sed 's/-[0-9.]*$//' | sed 's/-typescript$//')
+    base_type=$(echo "$project_type" | sed 's/-[0-9.]*$//' | sed 's/-typescript$//') || true
 
     # Map to template file
     local template_file=""
@@ -69,7 +69,7 @@ get_dod_template_path() {
     local templates_dir="${2:-$DOD_TEMPLATES_DIR}"
 
     local base_type
-    base_type=$(echo "$project_type" | sed 's/-[0-9.]*$//' | sed 's/-typescript$//')
+    base_type=$(echo "$project_type" | sed 's/-[0-9.]*$//' | sed 's/-typescript$//') || true
 
     case "$base_type" in
         symfony|laravel|php)