mirror of
https://gitee.com/mateos/mateclaw.git
synced 2026-09-13 19:23:42 +08:00
* feat(wiki): unify raw materials & source watcher into a Sources tab with per-KB auto-sync The raw-material directory scan and the Advanced "source watcher" sub-tab were the same engine (same kb.sourceDirectory, same WikiDirectoryScanService) split across two surfaces with two editable directory inputs. Merge them into one "Sources" tab (upload / paste / directory manual scan + auto-sync toggle + the raw-material list) and drop the watcher sub-tab from Advanced. Auto-sync is now per-KB opt-in: a new watcher_enabled column (V146) gates the periodic scan per knowledge base. The server-global mate.wiki.watcher-enabled stays as an ops master switch — a KB is auto-scanned only when both are on (AND). Manual scans are unaffected. Scan interval stays global for now (tracked separately). Closes matevip/mateclaw#314 * docs(wiki): document source-watcher global switch env vars Expose MATE_WIKI_WATCHER_ENABLED / MATE_WIKI_WATCHER_INTERVAL_MS as explicit placeholders in application-mysql.yml, .env.example and docker-compose.yml, mirroring MATE_WIKI_ALLOWED_SOURCE_ROOTS. Notes the AND semantics (global ops gate + per-KB toggle) so operators know the global switch alone is not sufficient.
128 lines
5.8 KiB
YAML
128 lines
5.8 KiB
YAML
version: '3.8'
|
||
|
||
services:
|
||
# MySQL 数据库
|
||
#
|
||
# ⚠️ 密码通过环境变量传入,必须从 .env 文件提供。首次部署前:
|
||
# 1. cp .env.example .env
|
||
# 2. 编辑 .env 把 DB_ROOT_PASSWORD / DB_PASSWORD 改成强密码
|
||
# 未设置会直接在 `docker compose up` 时报错,避免把默认密码带到生产环境。
|
||
mysql:
|
||
image: mysql:8.0
|
||
container_name: mateclaw-mysql
|
||
restart: unless-stopped
|
||
environment:
|
||
MYSQL_ROOT_PASSWORD: ${DB_ROOT_PASSWORD:?DB_ROOT_PASSWORD is required in .env}
|
||
MYSQL_DATABASE: ${DB_NAME:-mateclaw}
|
||
MYSQL_USER: ${DB_USERNAME:-mateclaw}
|
||
MYSQL_PASSWORD: ${DB_PASSWORD:?DB_PASSWORD is required in .env}
|
||
TZ: Asia/Shanghai
|
||
ports:
|
||
- "3306:3306"
|
||
volumes:
|
||
- mysql_data:/var/lib/mysql
|
||
# Schema and seed data are managed by Flyway on application startup.
|
||
# Do NOT mount legacy schema.sql / data.sql here — Flyway creates all
|
||
# tables from V1 baseline and applies incremental migrations automatically.
|
||
command: --character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci
|
||
healthcheck:
|
||
test: ["CMD", "mysqladmin", "ping", "-h", "localhost"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
# SearXNG 搜索引擎(keyless 搜索 provider)
|
||
#
|
||
# The custom image at docker/searxng/ bakes in settings.yml so the sidecar
|
||
# works out of the box (upstream image ships JSON disabled + Limiter enabled,
|
||
# both of which silently break mateclaw's SearXNGSearchProvider).
|
||
# No host bind-mount — edit docker/searxng/settings.yml and rebuild.
|
||
searxng:
|
||
build:
|
||
context: ./docker/searxng
|
||
container_name: mateclaw-searxng
|
||
restart: unless-stopped
|
||
environment:
|
||
- SEARXNG_BASE_URL=http://searxng:8080
|
||
- SEARXNG_SECRET=${SEARXNG_SECRET:-mateclaw-dev-searxng-secret-change-me}
|
||
- UWSGI_WORKERS=2
|
||
- UWSGI_THREADS=4
|
||
ports:
|
||
- "8088:8080"
|
||
healthcheck:
|
||
# Healthz needs json format, so this also doubles as an integration check.
|
||
test: ["CMD", "wget", "--spider", "-q", "http://localhost:8080/healthz"]
|
||
interval: 30s
|
||
timeout: 5s
|
||
retries: 3
|
||
|
||
# MateClaw 后端服务
|
||
mateclaw-server:
|
||
build:
|
||
context: .
|
||
dockerfile: mateclaw-server/Dockerfile
|
||
args:
|
||
MAVEN_FLAGS: ${MAVEN_FLAGS:-}
|
||
container_name: mateclaw-server
|
||
restart: unless-stopped
|
||
depends_on:
|
||
mysql:
|
||
condition: service_healthy
|
||
searxng:
|
||
condition: service_healthy
|
||
environment:
|
||
SPRING_PROFILES_ACTIVE: mysql
|
||
DB_HOST: mysql
|
||
DB_PORT: 3306
|
||
DB_NAME: ${DB_NAME:-mateclaw}
|
||
DB_USERNAME: ${DB_USERNAME:-mateclaw}
|
||
DB_PASSWORD: ${DB_PASSWORD:?DB_PASSWORD is required in .env}
|
||
# LLM provider keys (DashScope / OpenAI / Anthropic / DeepSeek / Kimi / …) are
|
||
# NOT configured via env vars. After startup, add providers in the admin UI:
|
||
# Settings → Models → Add Provider
|
||
# Keys are stored in mate_model_provider and hot-reloaded.
|
||
SERPER_API_KEY: ${SERPER_API_KEY:-}
|
||
JWT_SECRET: ${JWT_SECRET:-}
|
||
MATECLAW_CORS_ALLOWED_ORIGINS: ${MATECLAW_CORS_ALLOWED_ORIGINS:-}
|
||
# SearXNG: tell the app where to reach the sidecar container
|
||
SEARXNG_BASE_URL: ${SEARXNG_BASE_URL:-http://searxng:8080}
|
||
# Browser automation: the runtime image (mcr.microsoft.com/playwright:*)
|
||
# bakes Chromium + system libs + fonts in, so the tool works out of the box.
|
||
# Override these if you want to attach to an external Chrome (CDP sidecar):
|
||
MATECLAW_BROWSER_CDP_URL: ${MATECLAW_BROWSER_CDP_URL:-}
|
||
MATECLAW_BROWSER_CHROME_PATH: ${MATECLAW_BROWSER_CHROME_PATH:-}
|
||
MATECLAW_BROWSER_CHANNEL: ${MATECLAW_BROWSER_CHANNEL:-}
|
||
# OAuth 模式默认保持 auto:localhost 访问走 LOCAL,IP/域名访问走 DEVICE_CODE。
|
||
# 本机 Docker 若要强制使用 localhost:1455 回调,可在 .env 显式设为 local。
|
||
MATECLAW_OAUTH_OPENAI_DEPLOYMENT_MODE: ${MATECLAW_OAUTH_OPENAI_DEPLOYMENT_MODE:-}
|
||
MATECLAW_OAUTH_OPENAI_CALLBACK_BIND_HOST: ${MATECLAW_OAUTH_OPENAI_CALLBACK_BIND_HOST:-0.0.0.0}
|
||
# Wiki 知识库目录扫描白名单(逗号分隔,留空则禁止所有目录扫描)。
|
||
# 示例:MATE_WIKI_ALLOWED_SOURCE_ROOTS=/data/wiki,/opt/docs
|
||
# 记得同步在 volumes 里把宿主机路径挂进容器。
|
||
MATE_WIKI_ALLOWED_SOURCE_ROOTS: ${MATE_WIKI_ALLOWED_SOURCE_ROOTS:-}
|
||
# Wiki 知识源自动同步总开关(运维总闸,默认关)。AND 语义:全局开关与
|
||
# 每个知识库自己的「自动同步」开关都开,该库才会被定时扫描。
|
||
# 间隔单位毫秒,默认 5 分钟。
|
||
MATE_WIKI_WATCHER_ENABLED: ${MATE_WIKI_WATCHER_ENABLED:-false}
|
||
MATE_WIKI_WATCHER_INTERVAL_MS: ${MATE_WIKI_WATCHER_INTERVAL_MS:-300000}
|
||
# Skill 工作区根目录。放在 /app/data 下,让现有的 server_data 卷一并持久化
|
||
# 已安装的 skill、运行时积累的 LESSONS.md 以及 skill 运行产物,容器重启不丢。
|
||
# 内置 skill 仍由 JAR classpath 每次启动现场释放,空卷不会丢内置文件。
|
||
MATECLAW_SKILL_WORKSPACE_ROOT: ${MATECLAW_SKILL_WORKSPACE_ROOT:-/app/data/skills}
|
||
# Chromium needs a real /dev/shm. Docker defaults to 64MB which causes
|
||
# SIGBUS / "Target page closed" errors under load. 2GB is the usual
|
||
# recommendation for Playwright / headless chrome.
|
||
shm_size: 2gb
|
||
ports:
|
||
- "18080:18088" # host:container — app listens on 18088 inside the container
|
||
- "1455:1455"
|
||
volumes:
|
||
# server_data covers /app/data — H2 DB, wiki-uploads, AND the skill
|
||
# workspace (MATECLAW_SKILL_WORKSPACE_ROOT=/app/data/skills above), so a
|
||
# single volume persists everything. No separate skills volume needed.
|
||
- server_data:/app/data
|
||
|
||
volumes:
|
||
mysql_data:
|
||
server_data:
|