feat(replication): расхардкод хоста + секреты нового хоста + smoke-runbook

Фундамент тиража 10-common (эпик ORCH-10): платформа разворачивается на
новой инфре без правки кода — только env/конфиг. Каждый дефолт = боевому
значению (пустой .env => поведение 1:1, kill-switch-природа, NFR-2);
STAGE_TRANSITIONS/QG_CHECKS/check_*/machine-verdict/схема БД не тронуты.

- config: agent_home_dir / agent_git_name / git_email_domain / staging_port
  (ADR-001 D2/D4); код-блокеры A1-A4 закрыты: plane_sync ссылки из
  gitea_public_url+gitea_owner, launcher - единый agent_git_env() (x2 места),
  self_deploy/post_deploy - HOME+домен из Settings (имена системных акторов -
  платформенные литералы)
- image_freshness: staging_port из конфига + fail-closed guard
  staging_port == прод-порт -> отказ ДО ssh/build (инвариант ORCH-058 AC-9
  стал исполняемым); REPO= передаётся хуку явно обоими инвокерами (D7)
- SELF_HOSTING_REPO - нормативная платформенная константа (D3, пин-тест)
- compose: полная ${VAR:-default}-интерполяция (реестр B, карта D6); группа
  ORCH-040 uid/gid/HOME/маунты двигается согласованно (build.args APP_*);
  group_add "МИНА 1" сохранён x3; оба app-сервиса с явным command:
- Dockerfile: ARG APP_UID/APP_GID/APP_USER/APP_HOME (CMD exec-form 8500
  сознательно не тронут - D5); deploy-hook: REPO="${REPO:-...}" (D1 реестра)
- секреты: stdlib scripts/gen_secrets.py (token_hex(32); печать по умолчанию;
  --write никогда не перезаписывает существующий .env молча, exit=2;
  перезапись только --force); .env.example дополнен до полноты ключей старта
- доки: новый docs/operations/REPLICATION.md (карта env, чек-лист секретов,
  smoke-процедура с PASS/FAIL, границы 10-common/Lite/Bundled), INFRA.md,
  README, CLAUDE.md, CHANGELOG
- анти-регресс: tests/test_no_host_hardcodes.py (tokenize-сканер запрещённых
  литералов, config-модули - структурное исключение, allowlist пуст,
  негативная самопроверка) + test_host_config_keys / test_infra_parametrization
  / test_secrets_gen / test_replication_smoke; согласованные структурные
  правки test_orch040_compose (судит резолв дефолтов) и
  test_deploy_hook_rollback_sim (REPO через env-override = контракт D7)

Полный регресс: 1764 passed.

Refs: ORCH-101

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

docker-compose.yml

@@ -1,42 +1,65 @@
+# ORCH-101 (replication foundation): every host-specific value is interpolated
+# as ${VAR:-default}; the defaults equal the current production values, so an
+# empty environment resolves to a byte-for-byte equivalent of the previous file
+# (zero regression, BR-5). Compose reads ${VAR} from the project `.env` /shell —
+# NOT from a service's env_file (so .env.staging does NOT interpolate); the
+# Settings-shared names (ORCH_AGENT_HOME_DIR, ORCH_STAGING_PORT, ...) are read
+# by pydantic from env_file AND by compose from .env — one name per fact (D1).
+# Container-side paths (/app/data, /repos, /opt/claude-code, docker.sock) are a
+# container-layout convention, NOT host values — deliberately not parametrised.
+# See docs/operations/REPLICATION.md for the full variable map.
 services:
   orchestrator:
-    build: .
+    build:
+      context: .
+      # ORCH-101 (D5): uid/gid/home move as ONE coherent group with the runtime
+      # user: and the mount targets below (ORCH-040 invariant).
+      args:
+        APP_UID: ${ORCH_RUN_UID:-1000}
+        APP_GID: ${ORCH_RUN_GID:-1000}
+        APP_HOME: ${ORCH_AGENT_HOME_DIR:-/home/slin}
     container_name: orchestrator
     restart: unless-stopped
     # ORCH-040: бежим под uid:gid хоста (slin=1000:1000), а не root, чтобы
     # артефакты конвейера (worktree + docs) создавались как slin:slin и git на
     # хосте работал без ручного chown. Доступ к docker.sock сохранён через
     # group_add: ["999"] (МИНА 1 — НЕ удалять). См. ADR-001 ORCH-040.
-    user: "1000:1000"
+    user: "${ORCH_RUN_UID:-1000}:${ORCH_RUN_GID:-1000}"
     # init: true injects docker-init (tini) as PID 1 so reparented grandchild
     # processes from the claude/node subprocess tree are reaped (no zombies, B-2).
     init: true
     network_mode: host
+    # ORCH-101 (D5): the prod port is configurable on the compose layer (the
+    # Dockerfile CMD keeps its exec-form 8500 default — ADR-001 D5); the default
+    # resolves byte-for-byte to the previous image CMD. Reuses the existing
+    # ORCH_DEPLOY_PROD_TARGET_PORT (no second truth about the prod port).
+    command: ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "${ORCH_DEPLOY_PROD_TARGET_PORT:-8500}"]
     volumes:
       - ./data:/app/data
-      - /home/slin/repos:/repos
+      - ${ORCH_HOST_REPOS_DIR:-/home/slin/repos}:/repos
       - /var/run/docker.sock:/var/run/docker.sock
-      - /usr/lib/node_modules/@anthropic-ai/claude-code:/opt/claude-code:ro
-      - /usr/bin/node:/usr/bin/node:ro
-      - /home/slin/.claude:/home/slin/.claude
-      - /home/slin/.claude.json:/home/slin/.claude.json:ro
-      # ORCH-040: target согласован с HOME=/home/slin (launcher), не /root/.ssh.
-      - /home/slin/.orchestrator-ssh:/home/slin/.ssh:ro
+      - ${ORCH_HOST_CLAUDE_CODE_DIR:-/usr/lib/node_modules/@anthropic-ai/claude-code}:/opt/claude-code:ro
+      - ${ORCH_HOST_NODE_BIN:-/usr/bin/node}:/usr/bin/node:ro
+      - ${ORCH_HOST_CLAUDE_DIR:-/home/slin/.claude}:${ORCH_AGENT_HOME_DIR:-/home/slin}/.claude
+      - ${ORCH_HOST_CLAUDE_JSON:-/home/slin/.claude.json}:${ORCH_AGENT_HOME_DIR:-/home/slin}/.claude.json:ro
+      # ORCH-040: target согласован с HOME (launcher: settings.agent_home_dir),
+      # не /root/.ssh — обе стороны двигаются одной переменной ORCH_AGENT_HOME_DIR.
+      - ${ORCH_HOST_SSH_DIR:-/home/slin/.orchestrator-ssh}:${ORCH_AGENT_HOME_DIR:-/home/slin}/.ssh:ro
     env_file: .env
     environment:
       - ORCH_REPOS_DIR=/repos
-      - ORCH_HOST_REPOS_DIR=/home/slin/repos
+      - ORCH_HOST_REPOS_DIR=${ORCH_HOST_REPOS_DIR:-/home/slin/repos}
       # legacy enduro deployer (read via os.environ, keep as-is):
-      - DEPLOY_SSH_USER=slin
+      - DEPLOY_SSH_USER=${ORCH_DEPLOY_SSH_USER:-slin}
       - DEPLOY_SSH_HOST=127.0.0.1
-      - DEPLOY_HOOK_SCRIPT=/home/slin/bin/enduro-deploy-hook.sh
+      - DEPLOY_HOOK_SCRIPT=${DEPLOY_HOOK_SCRIPT:-/home/slin/bin/enduro-deploy-hook.sh}
       # ORCH-036 self-deploy (read via pydantic ORCH_ prefix; host-network -> 127.0.0.1, ssh key mounted):
-      - ORCH_DEPLOY_SSH_USER=slin
+      - ORCH_DEPLOY_SSH_USER=${ORCH_DEPLOY_SSH_USER:-slin}
       - ORCH_DEPLOY_SSH_HOST=127.0.0.1
       - ORCH_DEPLOY_HOOK_SCRIPT=scripts/orchestrator-deploy-hook.sh
-      - ORCH_DEPLOY_HOST_REPO_PATH=/home/slin/repos/orchestrator
+      - ORCH_DEPLOY_HOST_REPO_PATH=${ORCH_DEPLOY_HOST_REPO_PATH:-/home/slin/repos/orchestrator}
     group_add:
-      - "999"
+      - "${ORCH_DOCKER_GID:-999}"
 
   # ORCH-100 (FND/F1b): sidecar-watchdog — the monitoring brain in a SEPARATE
   # container (observer separated from observed, ADR-001 D2). Deploying it builds
@@ -60,7 +83,7 @@ services:
     mem_reservation: 32m
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock:ro
-      - /home/slin/repos:/repos:ro
+      - ${ORCH_HOST_REPOS_DIR:-/home/slin/repos}:/repos:ro
       - ./data:/app/data:ro
     # Optional env_file (required: false): a missing .env.watchdog must NOT fail
     # `docker compose up` for the prod orchestrator (self-hosting safety). Absent
@@ -69,7 +92,7 @@ services:
       - path: .env.watchdog
         required: false
     group_add:
-      - "999"
+      - "${ORCH_DOCKER_GID:-999}"
 
   # ORCH-31: staging instance (port 8501, isolated DB).
   # Starts ONLY with: docker compose --profile staging up -d orchestrator-staging
@@ -77,35 +100,42 @@ services:
   orchestrator-staging:
     profiles:
       - staging
-    build: .
+    build:
+      context: .
+      args:
+        APP_UID: ${ORCH_RUN_UID:-1000}
+        APP_GID: ${ORCH_RUN_GID:-1000}
+        APP_HOME: ${ORCH_AGENT_HOME_DIR:-/home/slin}
     container_name: orchestrator-staging
     restart: unless-stopped
     # ORCH-040: тот же uid хоста, что и у prod (см. комментарий выше / ADR-001).
-    user: "1000:1000"
+    user: "${ORCH_RUN_UID:-1000}:${ORCH_RUN_GID:-1000}"
     init: true
     network_mode: host
-    command: ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8501"]
+    # ORCH-101 (D4): the same ORCH_STAGING_PORT that settings.staging_port reads —
+    # the image_freshness rebuild target and the listening port can never drift.
+    command: ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "${ORCH_STAGING_PORT:-8501}"]
     volumes:
       - ./data/staging:/app/data
-      - /home/slin/repos:/repos
+      - ${ORCH_HOST_REPOS_DIR:-/home/slin/repos}:/repos
       - /var/run/docker.sock:/var/run/docker.sock
-      - /usr/lib/node_modules/@anthropic-ai/claude-code:/opt/claude-code:ro
-      - /usr/bin/node:/usr/bin/node:ro
-      - /home/slin/.claude:/home/slin/.claude
-      - /home/slin/.claude.json:/home/slin/.claude.json:ro
-      # ORCH-040: target согласован с HOME=/home/slin (launcher), не /root/.ssh.
-      - /home/slin/.orchestrator-ssh:/home/slin/.ssh:ro
+      - ${ORCH_HOST_CLAUDE_CODE_DIR:-/usr/lib/node_modules/@anthropic-ai/claude-code}:/opt/claude-code:ro
+      - ${ORCH_HOST_NODE_BIN:-/usr/bin/node}:/usr/bin/node:ro
+      - ${ORCH_HOST_CLAUDE_DIR:-/home/slin/.claude}:${ORCH_AGENT_HOME_DIR:-/home/slin}/.claude
+      - ${ORCH_HOST_CLAUDE_JSON:-/home/slin/.claude.json}:${ORCH_AGENT_HOME_DIR:-/home/slin}/.claude.json:ro
+      # ORCH-040: target согласован с HOME (settings.agent_home_dir), не /root/.ssh.
+      - ${ORCH_HOST_SSH_DIR:-/home/slin/.orchestrator-ssh}:${ORCH_AGENT_HOME_DIR:-/home/slin}/.ssh:ro
     env_file: .env.staging
     environment:
       - ORCH_REPOS_DIR=/repos
-      - ORCH_HOST_REPOS_DIR=/home/slin/repos
-      - DEPLOY_SSH_USER=slin
+      - ORCH_HOST_REPOS_DIR=${ORCH_HOST_REPOS_DIR:-/home/slin/repos}
+      - DEPLOY_SSH_USER=${ORCH_DEPLOY_SSH_USER:-slin}
       - DEPLOY_SSH_HOST=127.0.0.1
-      - DEPLOY_HOOK_SCRIPT=/home/slin/bin/enduro-deploy-hook.sh
+      - DEPLOY_HOOK_SCRIPT=${DEPLOY_HOOK_SCRIPT:-/home/slin/bin/enduro-deploy-hook.sh}
       # Staging DB is isolated via ./data/staging volume mount.
       # Inside the container the path remains /app/data/orchestrator.db (same default),
-      # but on the host it physically lives at ./data/staging/orchestrator.db — 
+      # but on the host it physically lives at ./data/staging/orchestrator.db —
       # completely separate from prod ./data/orchestrator.db.
       - ORCH_DB_PATH=/app/data/orchestrator.db
     group_add:
-      - "999"
+      - "${ORCH_DOCKER_GID:-999}"