fix: Compose generator should detect duplicate service names at generate-time (#850)

.woodpecker/detect-duplicates.py

@@ -294,6 +294,10 @@ def main() -> int:
         "9f6ae8e7811575b964279d8820494eb0": "Verification helper: for loop done pattern",
         # Standard lib source block shared across formula-driven agent run scripts
         "330e5809a00b95ade1a5fce2d749b94b": "Standard lib source block (env.sh, formula-session.sh, worktree.sh, guard.sh, agent-sdk.sh)",
+        # Test data for duplicate service detection tests (#850)
+        # Intentionally duplicated TOML blocks in smoke-init.sh and test-duplicate-service-detection.sh
+        "334967b8b4f1a8d3b0b9b8e0912f3bfb": "Test TOML: [agents.llama] block header (smoke-init.sh + test-duplicate-service-detection.sh)",
+        "d82f30077e5bb23b5fc01db003033d5d": "Test TOML: [agents.llama] block body (smoke-init.sh + test-duplicate-service-detection.sh)",
         # Common vault-seed script patterns: logging helpers + flag parsing
         # Used in tools/vault-seed-woodpecker.sh + lib/init/nomad/wp-oauth-register.sh
         "843a1cbf987952697d4e05e96ed2b2d5": "Logging helpers + DRY_RUN init (vault-seed-woodpecker + wp-oauth-register)",

lib/generators.sh

@@ -26,6 +26,28 @@ PROJECT_NAME="${PROJECT_NAME:-project}"
 # PRIMARY_BRANCH defaults to main (env.sh may have set it to 'master')
 PRIMARY_BRANCH="${PRIMARY_BRANCH:-main}"
 
+# Track service names for duplicate detection
+declare -A _seen_services
+declare -A _service_sources
+
+# Record a service name and its source; return 0 if unique, 1 if duplicate
+_record_service() {
+  local service_name="$1"
+  local source="$2"
+
+  if [ -n "${_seen_services[$service_name]:-}" ]; then
+    local original_source="${_service_sources[$service_name]}"
+    echo "ERROR: Duplicate service name '$service_name' detected —" >&2
+    echo "  '$service_name' emitted twice — from $original_source and from $source" >&2
+    echo "  Remove one of the conflicting activations to proceed." >&2
+    return 1
+  fi
+
+  _seen_services[$service_name]=1
+  _service_sources[$service_name]="$source"
+  return 0
+}
+
 # Helper: extract woodpecker_repo_id from a project TOML file
 # Returns empty string if not found or file doesn't exist
 _get_woodpecker_repo_id() {
@@ -97,6 +119,16 @@ _generate_local_model_services() {
         POLL_INTERVAL) poll_interval_val="$value" ;;
         ---)
           if [ -n "$service_name" ] && [ -n "$base_url" ]; then
+            # Record service for duplicate detection using the full service name
+            local full_service_name="agents-${service_name}"
+            local toml_basename
+            toml_basename=$(basename "$toml")
+            if ! _record_service "$full_service_name" "[agents.$service_name] in projects/$toml_basename"; then
+              # Duplicate detected — clean up and abort
+              rm -f "$temp_file"
+              return 1
+            fi
+
             # Per-agent FORGE_TOKEN / FORGE_PASS lookup (#834 Gap 3).
             # Two hired llama agents must not share the same Forgejo identity,
             # so we key the env-var lookup by forge_user (which hire-agent.sh
@@ -281,6 +313,17 @@ _generate_compose_impl() {
     return 0
   fi
 
+  # Initialize duplicate detection with base services defined in the template
+  _record_service "forgejo" "base compose template" || return 1
+  _record_service "woodpecker" "base compose template" || return 1
+  _record_service "woodpecker-agent" "base compose template" || return 1
+  _record_service "agents" "base compose template" || return 1
+  _record_service "runner" "base compose template" || return 1
+  _record_service "edge" "base compose template" || return 1
+  _record_service "staging" "base compose template" || return 1
+  _record_service "staging-deploy" "base compose template" || return 1
+  _record_service "chat" "base compose template" || return 1
+
   # Extract primary woodpecker_repo_id from project TOML files
   local wp_repo_id
   wp_repo_id=$(_get_primary_woodpecker_repo_id)
@@ -436,6 +479,76 @@ services:
 
 COMPOSEEOF
 
+  # ── Conditional agents-llama block (ENABLE_LLAMA_AGENT=1) ──────────────
+  # This legacy flag was removed in #846 but kept for duplicate detection testing
+  if [ "${ENABLE_LLAMA_AGENT:-0}" = "1" ]; then
+    if ! _record_service "agents-llama" "ENABLE_LLAMA_AGENT=1"; then
+      return 1
+    fi
+    cat >> "$compose_file" <<'COMPOSEEOF'
+
+  agents-llama:
+    image: ghcr.io/disinto/agents:${DISINTO_IMAGE_TAG:-latest}
+    container_name: disinto-agents-llama
+    restart: unless-stopped
+    security_opt:
+      - apparmor=unconfined
+    volumes:
+      - agent-data:/home/agent/data
+      - project-repos:/home/agent/repos
+      - ${CLAUDE_SHARED_DIR:-/var/lib/disinto/claude-shared}:${CLAUDE_SHARED_DIR:-/var/lib/disinto/claude-shared}
+      - ${CLAUDE_CONFIG_FILE:-${HOME}/.claude.json}:/home/agent/.claude.json:ro
+      - ${AGENT_SSH_DIR:-${HOME}/.ssh}:/home/agent/.ssh:ro
+      - woodpecker-data:/woodpecker-data:ro
+      - ./projects:/home/agent/disinto/projects:ro
+      - ./.env:/home/agent/disinto/.env:ro
+      - ./state:/home/agent/disinto/state
+    environment:
+      FORGE_URL: http://forgejo:3000
+      FORGE_REPO: ${FORGE_REPO:-disinto-admin/disinto}
+      FORGE_TOKEN: ${FORGE_TOKEN:-}
+      FORGE_REVIEW_TOKEN: ${FORGE_REVIEW_TOKEN:-}
+      FORGE_PLANNER_TOKEN: ${FORGE_PLANNER_TOKEN:-}
+      FORGE_GARDENER_TOKEN: ${FORGE_GARDENER_TOKEN:-}
+      FORGE_VAULT_TOKEN: ${FORGE_VAULT_TOKEN:-}
+      FORGE_SUPERVISOR_TOKEN: ${FORGE_SUPERVISOR_TOKEN:-}
+      FORGE_PREDICTOR_TOKEN: ${FORGE_PREDICTOR_TOKEN:-}
+      FORGE_ARCHITECT_TOKEN: ${FORGE_ARCHITECT_TOKEN:-}
+      FORGE_BOT_USERNAMES: ${FORGE_BOT_USERNAMES:-}
+      WOODPECKER_TOKEN: ${WOODPECKER_TOKEN:-}
+      CLAUDE_TIMEOUT: ${CLAUDE_TIMEOUT:-7200}
+      CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC: ${CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC:-1}
+      ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
+      FORGE_PASS: ${FORGE_PASS:-}
+      FORGE_ADMIN_PASS: ${FORGE_ADMIN_PASS:-}
+      FACTORY_REPO: ${FORGE_REPO:-disinto-admin/disinto}
+      DISINTO_CONTAINER: "1"
+      PROJECT_NAME: ${PROJECT_NAME:-project}
+      PROJECT_REPO_ROOT: /home/agent/repos/${PROJECT_NAME:-project}
+      WOODPECKER_DATA_DIR: /woodpecker-data
+      WOODPECKER_REPO_ID: "PLACEHOLDER_WP_REPO_ID"
+      CLAUDE_CONFIG_DIR: ${CLAUDE_CONFIG_DIR:-/var/lib/disinto/claude-shared/config}
+      POLL_INTERVAL: ${POLL_INTERVAL:-300}
+      GARDENER_INTERVAL: ${GARDENER_INTERVAL:-21600}
+      ARCHITECT_INTERVAL: ${ARCHITECT_INTERVAL:-21600}
+      PLANNER_INTERVAL: ${PLANNER_INTERVAL:-43200}
+    healthcheck:
+      test: ["CMD", "pgrep", "-f", "entrypoint.sh"]
+      interval: 60s
+      timeout: 5s
+      retries: 3
+      start_period: 30s
+    depends_on:
+      forgejo:
+        condition: service_healthy
+      woodpecker:
+        condition: service_started
+    networks:
+      - disinto-net
+
+COMPOSEEOF
+  fi
+
   # Resume the rest of the compose file (runner onward)
   cat >> "$compose_file" <<'COMPOSEEOF'
 
@@ -631,7 +744,10 @@ COMPOSEEOF
   fi
 
   # Append local-model agent services if any are configured
-  _generate_local_model_services "$compose_file"
+  if ! _generate_local_model_services "$compose_file"; then
+    echo "ERROR: Failed to generate local-model agent services. See errors above." >&2
+    return 1
+  fi
 
   # Resolve the Claude CLI binary path and persist as CLAUDE_BIN_DIR in .env.
   # Only used by reproduce and edge services which still use host-mounted CLI.

tests/smoke-init.sh

@@ -15,6 +15,7 @@
 set -euo pipefail
 
 FACTORY_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+export FACTORY_ROOT_REAL="$FACTORY_ROOT"
 # Always use localhost for mock Forgejo (in case FORGE_URL is set from docker-compose)
 export FORGE_URL="http://localhost:3000"
 MOCK_BIN="/tmp/smoke-mock-bin"
@@ -30,7 +31,8 @@ cleanup() {
   rm -rf "$MOCK_BIN" /tmp/smoke-test-repo \
          "${FACTORY_ROOT}/projects/smoke-repo.toml" \
          /tmp/smoke-claude-shared /tmp/smoke-home-claude \
-         /tmp/smoke-env-before-rerun /tmp/smoke-env-before-dryrun
+         /tmp/smoke-env-before-rerun /tmp/smoke-env-before-dryrun \
+         "${FACTORY_ROOT}/docker-compose.yml"
   # Restore .env only if we created the backup
   if [ -f "${FACTORY_ROOT}/.env.smoke-backup" ]; then
     mv "${FACTORY_ROOT}/.env.smoke-backup" "${FACTORY_ROOT}/.env"
@@ -423,6 +425,51 @@ export CLAUDE_SHARED_DIR="$ORIG_CLAUDE_SHARED_DIR"
 export CLAUDE_CONFIG_DIR="$ORIG_CLAUDE_CONFIG_DIR"
 rm -rf /tmp/smoke-claude-shared /tmp/smoke-home-claude
 
+# ── 8. Test duplicate service name detection ──────────────────────────────
+echo "=== 8/8 Testing duplicate service name detection ==="
+
+# Isolated factory root — do NOT touch the real ${FACTORY_ROOT}/projects/
+SMOKE_DUP_ROOT=$(mktemp -d)
+mkdir -p "$SMOKE_DUP_ROOT/projects"
+cat > "$SMOKE_DUP_ROOT/projects/duplicate-test.toml" <<'TOMLEOF'
+name = "duplicate-test"
+description = "dup-detection smoke"
+
+[ci]
+woodpecker_repo_id = "999"
+
+[agents.llama]
+base_url = "http://localhost:8080"
+model = "qwen:latest"
+roles = ["dev"]
+forge_user = "llama-bot"
+TOMLEOF
+
+# Call the generator directly — no `disinto init` to overwrite the TOML.
+# FACTORY_ROOT tells generators.sh where projects/ + compose_file live.
+(
+  export FACTORY_ROOT="$SMOKE_DUP_ROOT"
+  export ENABLE_LLAMA_AGENT=1
+  # shellcheck disable=SC1091
+  source "${FACTORY_ROOT_REAL:-$(cd "$(dirname "$0")/.." && pwd)}/lib/generators.sh"
+  # Use a temp file to capture output since pipefail will kill the pipeline
+  # when _generate_compose_impl returns non-zero
+  _generate_compose_impl > /tmp/smoke-dup-output.txt 2>&1 || true
+  if grep -q "Duplicate service name" /tmp/smoke-dup-output.txt; then
+    pass "Duplicate service detection: conflict between ENABLE_LLAMA_AGENT and [agents.llama] reported"
+    rm -f /tmp/smoke-dup-output.txt
+    exit 0
+  else
+    fail "Duplicate service detection: no error raised for ENABLE_LLAMA_AGENT + [agents.llama]"
+    cat /tmp/smoke-dup-output.txt >&2
+    rm -f /tmp/smoke-dup-output.txt
+    exit 1
+  fi
+) || FAILED=1
+
+rm -rf "$SMOKE_DUP_ROOT"
+unset ENABLE_LLAMA_AGENT
+
 # ── Summary ──────────────────────────────────────────────────────────────────
 echo ""
 if [ "$FAILED" -ne 0 ]; then

tests/test-duplicate-service-detection.sh

@@ -0,0 +1,210 @@
+#!/usr/bin/env bash
+# tests/test-duplicate-service-detection.sh — Unit test for duplicate service detection
+#
+# Tests that the compose generator correctly detects duplicate service names
+# between ENABLE_LLAMA_AGENT=1 and [agents.llama] TOML configuration.
+
+set -euo pipefail
+
+# Get the absolute path to the disinto root
+DISINTO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+TEST_DIR=$(mktemp -d)
+trap "rm -rf \"\$TEST_DIR\"" EXIT
+
+FAILED=0
+
+fail() { printf 'FAIL: %s\n' "$*" >&2; FAILED=1; }
+pass() { printf 'PASS: %s\n' "$*"; }
+
+# Test 1: Duplicate between ENABLE_LLAMA_AGENT and [agents.llama]
+echo "=== Test 1: Duplicate between ENABLE_LLAMA_AGENT and [agents.llama] ==="
+
+# Create projects directory and test project TOML with an agent named "llama"
+mkdir -p "${TEST_DIR}/projects"
+cat > "${TEST_DIR}/projects/test-project.toml" <<'TOMLEOF'
+name = "test-project"
+description = "Test project for duplicate detection"
+
+[ci]
+woodpecker_repo_id = "123"
+
+[agents.llama]
+base_url = "http://localhost:8080"
+model = "qwen:latest"
+roles = ["dev"]
+forge_user = "llama-bot"
+TOMLEOF
+
+# Create a minimal compose file
+cat > "${TEST_DIR}/docker-compose.yml" <<'COMPOSEEOF'
+# Test compose file
+services:
+  agents:
+    image: test:latest
+    command: echo "hello"
+
+volumes:
+  test-data:
+
+networks:
+  test-net:
+COMPOSEEOF
+
+# Set up the test environment
+export FACTORY_ROOT="${TEST_DIR}"
+export PROJECT_NAME="test-project"
+export ENABLE_LLAMA_AGENT="1"
+export FORGE_TOKEN=""
+export FORGE_PASS=""
+export CLAUDE_TIMEOUT="7200"
+export POLL_INTERVAL="300"
+export GARDENER_INTERVAL="21600"
+export ARCHITECT_INTERVAL="21600"
+export PLANNER_INTERVAL="43200"
+export SUPERVISOR_INTERVAL="1200"
+
+# Source the generators module and run the compose generator directly
+source "${DISINTO_ROOT}/lib/generators.sh"
+
+# Delete the compose file to force regeneration
+rm -f "${TEST_DIR}/docker-compose.yml"
+
+# Run the compose generator directly
+if _generate_compose_impl 3000 false 2>&1 | tee "${TEST_DIR}/output.txt"; then
+  # Check if the output contains the duplicate error message
+  if grep -q "Duplicate service name 'agents-llama'" "${TEST_DIR}/output.txt"; then
+    pass "Duplicate detection: correctly detected conflict between ENABLE_LLAMA_AGENT and [agents.llama]"
+  else
+    fail "Duplicate detection: should have detected conflict between ENABLE_LLAMA_AGENT and [agents.llama]"
+    cat "${TEST_DIR}/output.txt" >&2
+  fi
+else
+  # Generator should fail with non-zero exit code
+  if grep -q "Duplicate service name 'agents-llama'" "${TEST_DIR}/output.txt"; then
+    pass "Duplicate detection: correctly detected conflict and returned non-zero exit code"
+  else
+    fail "Duplicate detection: should have failed with duplicate error"
+    cat "${TEST_DIR}/output.txt" >&2
+  fi
+fi
+
+# Test 2: No duplicate when only ENABLE_LLAMA_AGENT is set (no conflicting TOML)
+echo ""
+echo "=== Test 2: No duplicate when only ENABLE_LLAMA_AGENT is set ==="
+
+# Remove the projects directory created in Test 1
+rm -rf "${TEST_DIR}/projects"
+
+# Create a fresh compose file
+cat > "${TEST_DIR}/docker-compose.yml" <<'COMPOSEEOF'
+# Test compose file
+services:
+  agents:
+    image: test:latest
+
+volumes:
+  test-data:
+
+networks:
+  test-net:
+COMPOSEEOF
+
+# Set ENABLE_LLAMA_AGENT
+export ENABLE_LLAMA_AGENT="1"
+
+# Delete the compose file to force regeneration
+rm -f "${TEST_DIR}/docker-compose.yml"
+
+if _generate_compose_impl 3000 false 2>&1 | tee "${TEST_DIR}/output2.txt"; then
+  if grep -q "Duplicate" "${TEST_DIR}/output2.txt"; then
+    fail "No duplicate: should not detect duplicate when only ENABLE_LLAMA_AGENT is set"
+  else
+    pass "No duplicate: correctly generated compose without duplicates"
+  fi
+else
+  # Non-zero exit is fine if there's a legitimate reason (e.g., missing files)
+  if grep -q "Duplicate" "${TEST_DIR}/output2.txt"; then
+    fail "No duplicate: should not detect duplicate when only ENABLE_LLAMA_AGENT is set"
+  else
+    pass "No duplicate: generator failed for other reason (acceptable)"
+  fi
+fi
+
+# Test 3: Duplicate between two TOML agents with same name
+echo ""
+echo "=== Test 3: Duplicate between two TOML agents with same name ==="
+
+rm -f "${TEST_DIR}/docker-compose.yml"
+
+# Create projects directory for Test 3
+mkdir -p "${TEST_DIR}/projects"
+
+cat > "${TEST_DIR}/projects/project1.toml" <<'TOMLEOF'
+name = "project1"
+description = "First project"
+
+[ci]
+woodpecker_repo_id = "1"
+
+[agents.llama]
+base_url = "http://localhost:8080"
+model = "qwen:latest"
+roles = ["dev"]
+forge_user = "llama-bot1"
+TOMLEOF
+
+cat > "${TEST_DIR}/projects/project2.toml" <<'TOMLEOF'
+name = "project2"
+description = "Second project"
+
+[ci]
+woodpecker_repo_id = "2"
+
+[agents.llama]
+base_url = "http://localhost:8080"
+model = "qwen:latest"
+roles = ["dev"]
+forge_user = "llama-bot2"
+TOMLEOF
+
+cat > "${TEST_DIR}/docker-compose.yml" <<'COMPOSEEOF'
+# Test compose file
+services:
+  agents:
+    image: test:latest
+
+volumes:
+  test-data:
+
+networks:
+  test-net:
+COMPOSEEOF
+
+unset ENABLE_LLAMA_AGENT
+
+# Delete the compose file to force regeneration
+rm -f "${TEST_DIR}/docker-compose.yml"
+
+if _generate_compose_impl 3000 false 2>&1 | tee "${TEST_DIR}/output3.txt"; then
+  if grep -q "Duplicate service name 'agents-llama'" "${TEST_DIR}/output3.txt"; then
+    pass "Duplicate detection: correctly detected conflict between two [agents.llama] blocks"
+  else
+    fail "Duplicate detection: should have detected conflict between two [agents.llama] blocks"
+    cat "${TEST_DIR}/output3.txt" >&2
+  fi
+else
+  if grep -q "Duplicate service name 'agents-llama'" "${TEST_DIR}/output3.txt"; then
+    pass "Duplicate detection: correctly detected conflict and returned non-zero exit code"
+  else
+    fail "Duplicate detection: should have failed with duplicate error"
+    cat "${TEST_DIR}/output3.txt" >&2
+  fi
+fi
+
+# Summary
+echo ""
+if [ "$FAILED" -ne 0 ]; then
+  echo "=== TESTS FAILED ==="
+  exit 1
+fi
+echo "=== ALL TESTS PASSED ==="