Files
knowledge-governance/compose.yaml
T
姚章浩 f4e1ecc5f1 feat(artifact): 钉钉取件优先走 dws(DingTalk Workspace CLI),老路径保留为回退
- artifact_fetch.py: 新增 dingtalk dws 取件器(adoc→doc export、axls→sheet 转换、其余→drive 直下),
  ARTIFACT_DINGTALK_FETCHER=dws|auto|legacy 三级开关,auto 仅对可重试错误回落老路径;
  平台侧判定(pick_suffix/SLIDES/magic/大小上限/sha256/spool/空壳检查)全部保留;
  结果 JSON 字段不变(Go runner 用 DisallowUnknownFields 解析 stdout),取件器来源只写 stderr。
- axls_to_xlsx.py: 纯标准库 axls→xlsx(文本写入 sharedStrings 以通过空壳判定)。
- dws_error_map.py: dws 错误→平台 {ok,code,retryable,missing};未分类错误默认不重试。
- Dockerfile: alpine 增加 gcompat/libc6-compat;dws v1.0.63 固定版本+sha256 校验;构建期 dws version 自检。
- compose.yaml: worker 增加 dws 环境与凭据挂载(DWS_HOME 方案,XDG_DATA_HOME 不被 dws 识别)。
- 测试: artifact_fetch_test 新增 11 项(路由/回落语义/契约字段锁定);dws_error_map 17 断言。
- 实测: 真容器(--read-only --tmpfs --user 1000:1000) 端到端 adoc/axls/pdf 3/3 成功,docx sha 与平台基准一致。
2026-10-09 10:57:11 +08:00

216 lines
7.9 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
name: knowledge-governance-p1
services:
postgres:
image: postgres:17-alpine
environment:
POSTGRES_DB: governance
POSTGRES_USER: governance
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_password
secrets:
- postgres_password
volumes:
- governance-pgdata:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U governance -d governance"]
interval: 5s
timeout: 3s
retries: 20
restart: unless-stopped
api:
build:
context: .
dockerfile: Dockerfile
command: ["/app/api"]
user: "${APP_UID:-1000}:${APP_GID:-1000}"
environment:
<<: &app-environment
DATABASE_URL: postgres://governance@postgres:5432/governance?sslmode=disable
PGPASSFILE: /run/secrets/pgpass
APP_ADDR: :8080
WORKER_POLL_INTERVAL: 1s
WORKER_LEASE_DURATION: 30s
WORKER_RETRY_DELAY: 5s
TEST_WEKNORA_BASE_URL: "${TEST_WEKNORA_BASE_URL:-}"
DINGTALK_LOGIN_SIDECAR_URL: "http://dingtalk-login:8091"
MINERU_BASE_URL: "${MINERU_BASE_URL:-}"
TEST_INTERNAL_WEKNORA_KB_ID: "${TEST_INTERNAL_WEKNORA_KB_ID:-1b52c140-2e18-4676-afc5-4c7d8d190a8c}"
TEST_EXTERNAL_WEKNORA_KB_ID: "${TEST_EXTERNAL_WEKNORA_KB_ID:-fd7db6aa-763a-46f1-84d2-ecc7c952a5ea}"
# P10 readiness probe reads the routing KB with the same scoped key.
TEST_WEKNORA_API_KEY_FILE: /run/secrets/test_weknora_api_key
TEST_WEKNORA_ALLOW_DOCKER_HTTP: "${TEST_WEKNORA_ALLOW_DOCKER_HTTP:-false}"
WORKER_LIVENESS_STALE_AFTER: "${WORKER_LIVENESS_STALE_AFTER:-2m}"
PRODUCTION_RELEASE_REQUESTS_ENABLED: ${PRODUCTION_RELEASE_REQUESTS_ENABLED:-false}
PRODUCTION_BACKUP_RESTORE_VERIFIED: ${PRODUCTION_BACKUP_RESTORE_VERIFIED:-false}
# Read-only probe of the production WeKnora endpoint; publishing keeps
# reading its target from RELEASE_CONFIG_FILE.
PRODUCTION_WEKNORA_BASE_URL: "${PRODUCTION_WEKNORA_BASE_URL:-}"
PRODUCTION_WEKNORA_API_KEY_FILE: "${PRODUCTION_WEKNORA_API_KEY_FILE:-}"
PRODUCTION_WEKNORA_ALLOW_DOCKER_HTTP: "${PRODUCTION_WEKNORA_ALLOW_DOCKER_HTTP:-false}"
secrets:
- pgpass
- test_weknora_api_key
depends_on:
postgres:
condition: service_healthy
healthcheck:
# P10: liveness only — a third-party outage must never restart the API.
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8080/livez"]
interval: 5s
timeout: 3s
retries: 20
read_only: true
tmpfs:
- /tmp
networks:
- default
- weknora-local
restart: unless-stopped
worker:
build:
context: .
dockerfile: Dockerfile
command: ["/app/worker"]
user: "${APP_UID:-1000}:${APP_GID:-1000}"
environment:
<<: *app-environment
WORKER_ID: worker-1
PP_SCAN_ENABLED: "${PP_SCAN_ENABLED:-false}"
PP_SCAN_ALLOWED_ROOT: "${PP_SCAN_CONTAINER_DATA_ROOT:-/home/zheromiku/dobot-portal-sync/data}"
PP_SCAN_LEDGER_PATH: "${PP_SCAN_CONTAINER_DATA_ROOT:-/home/zheromiku/dobot-portal-sync/data}/public-weknora-sync/state.jsonl"
PP_SCAN_MANIFEST_PATH: "${PP_SCAN_CONTAINER_DATA_ROOT:-/home/zheromiku/dobot-portal-sync/data}/public-documents/manifest.json"
TEST_WEKNORA_ENABLED: "${TEST_WEKNORA_ENABLED:-false}"
TEST_WEKNORA_ALLOW_DOCKER_HTTP: "${TEST_WEKNORA_ALLOW_DOCKER_HTTP:-false}"
TEST_WEKNORA_KB_ID: "${TEST_WEKNORA_KB_ID:-}"
TEST_WEKNORA_API_KEY_FILE: /run/secrets/test_weknora_api_key
GOVERNANCE_SPOOL_ROOT: /var/lib/governance/spool
INGESTION_SPOOL_ROOT: /var/lib/governance/ingestion
TEST_WEKNORA_HTTP_TIMEOUT: "${TEST_WEKNORA_HTTP_TIMEOUT:-60s}"
TEST_WEKNORA_POLL_INITIAL: "${TEST_WEKNORA_POLL_INITIAL:-10s}"
TEST_WEKNORA_POLL_MAX: "${TEST_WEKNORA_POLL_MAX:-60s}"
TEST_WEKNORA_STALLED_AFTER: "${TEST_WEKNORA_STALLED_AFTER:-30m}"
TEST_WEKNORA_MAX_UPLOAD_BYTES: "${TEST_WEKNORA_MAX_UPLOAD_BYTES:-52428800}"
TEST_ACCEPTANCE_POLICY_VERSION: "${TEST_ACCEPTANCE_POLICY_VERSION:-structural-v1}"
# DingTalk 取件走 dws(默认优先 dws,可重试失败回落老路径):dws|auto|legacy
ARTIFACT_DINGTALK_FETCHER: "${ARTIFACT_DINGTALK_FETCHER:-auto}"
DWS_BIN: /usr/local/bin/dws
DWS_CONFIG_DIR: /data/dws
# dws 的文件型 keychain 在 $HOME/.local/share/dws-cli(XDG_DATA_HOME 不被识别),
# 仅给 dws 子进程换 HOME,不动整个 worker 的 HOME。
DWS_HOME: /data/home
DWS_DISABLE_KEYCHAIN: "1"
SSL_CERT_FILE: /etc/ssl/certs/ca-certificates.crt
secrets:
- pgpass
- test_weknora_api_key
volumes:
- ./spool:/var/lib/governance/spool:ro
- ./spool/ingestion:/var/lib/governance/ingestion
- "${PP_SCAN_HOST_DATA_ROOT:-/home/zheromiku/dobot-portal-sync/data}:${PP_SCAN_CONTAINER_DATA_ROOT:-/home/zheromiku/dobot-portal-sync/data}:ro"
- /home/zheromiku/dingtalk_kb_download:/sources/dingtalk:ro
# dws 凭据:与宿主共享同一份 state(refresh token 是轮换制,不能在两处各留一份)
- /home/zheromiku/.dws:/data/dws
# dws 的文件型 keychain:必须有 $HOME/.local/share/dws-cli,故挂到 DWS_HOME 下
- /home/zheromiku/.local/share/dws-cli:/data/home/.local/share/dws-cli
- /home/zheromiku/tmp/alist:/sources/alist:ro
- /home/zheromiku/dobot-portal-sync:/sources/pp:ro
- ./secrets/dingtalk_capture.json:/run/source-secrets/dingtalk_capture.json:ro
- ./secrets/alist_connections.xlsx:/run/source-secrets/alist_connections.xlsx:ro
- ./secrets/alist_api_token:/run/source-secrets/alist_api_token:ro
- ./secrets/pp_credentials.json:/run/source-secrets/pp_credentials.json:ro
networks:
- default
- weknora-local
depends_on:
postgres:
condition: service_healthy
read_only: true
tmpfs:
- /tmp
restart: unless-stopped
release-worker:
build:
context: .
dockerfile: Dockerfile
command: ["/app/release-worker"]
user: "${APP_UID:-1000}:${APP_GID:-1000}"
environment:
<<: *app-environment
WORKER_ID: release-worker-1
RELEASE_WORKER_ENABLED: "false"
RELEASE_CONFIG_FILE: ""
secrets:
- pgpass
depends_on:
postgres:
condition: service_healthy
read_only: true
tmpfs:
- /tmp
restart: unless-stopped
dingtalk-login:
# Chromium profile for DingTalk scan sessions. The bind-mounted secrets
# directory is rw ONLY here; the worker keeps reading the capture read-only.
build:
context: ./services/dingtalk-login
image: knowledge-governance-dingtalk-login:local
user: "${APP_UID:-1000}:${APP_GID:-1000}"
environment:
CAPTURE_FILE: /run/source-secrets/dingtalk_capture.json
DINGTALK_STATE_FILE: /sources/dingtalk/data/dingtalk-internal/inventory-state.json
VERIFY_SPACE: "${DINGTALK_VERIFY_SPACE:-9JOGO6332vlBnm4Q}"
QR_TTL_MS: "300000"
volumes:
- ./secrets:/run/source-secrets
- /home/zheromiku/dingtalk_kb_download:/sources/dingtalk
- dingtalk-chromium-profile:/profile
security_opt:
- no-new-privileges:true
tmpfs:
- /tmp
healthcheck:
test: ["CMD", "node", "-e", "require('http').get('http://127.0.0.1:8091/healthz',r=>process.exit(r.statusCode===200?0:1)).on('error',()=>process.exit(1))"]
interval: 10s
timeout: 5s
retries: 30
start_period: 15s
restart: unless-stopped
web:
build:
context: .
dockerfile: Dockerfile.web
ports:
- "8088:8080"
depends_on:
api:
condition: service_healthy
read_only: true
tmpfs:
- /tmp
- /var/cache/nginx
- /var/run
restart: unless-stopped
secrets:
postgres_password:
file: ./secrets/postgres_password
pgpass:
file: ./secrets/pgpass
test_weknora_api_key:
file: ./secrets/test_weknora_api_key
volumes:
governance-pgdata:
dingtalk-chromium-profile:
networks:
weknora-local:
external: true
name: weknora071full-network