feat(browser-fetch): add lightpanda-backed fetch service and knowledge URL fallback

Adds a new browser-fetch microservice that wraps Lightpanda for rendering
JS-heavy pages, and wires it into the knowledge URL parser as a fallback
when the upstream link reader returns 403/429/5xx for an allow-listed
domain (e.g. zhuanlan.zhihu.com). Includes config/env plumbing, hot-reload
diff support, and full deploy assets (Dockerfile target, docker-compose,
k3s manifests, image-build/package scripts).
This commit is contained in:
2026-05-11 11:11:21 +08:00
parent 708a45ba16
commit 7f08d92958
22 changed files with 1770 additions and 8 deletions
+10 -1
View File
@@ -16,7 +16,7 @@ REGISTRY_PASSWORD="${REGISTRY_PASSWORD:-}"
REGISTRY_PLAIN_HTTP="${REGISTRY_PLAIN_HTTP:-true}"
REGISTRY_SCHEME="${REGISTRY_SCHEME:-}"
IMAGE_TAG="${IMAGE_TAG:-}"
IMAGE_LIST="${IMAGE_LIST:-tenant-api ops-api worker-generate kol-assist-worker scheduler frontend ops-web migrate}"
IMAGE_LIST="${IMAGE_LIST:-tenant-api browser-fetch ops-api worker-generate kol-assist-worker scheduler frontend ops-web migrate}"
DELETE_OLD_IMAGE_TAGS="${DELETE_OLD_IMAGE_TAGS:-true}"
PUSH_LATEST="${PUSH_LATEST:-true}"
FORCE_BUILD="${FORCE_BUILD:-false}"
@@ -257,6 +257,15 @@ build_image() {
-f "${REPO_ROOT}/server/Dockerfile" \
"${REPO_ROOT}/server"
;;
browser-fetch)
docker build "${platform_args[@]}" \
--target browser-fetch \
--build-arg "SERVICE=browser-fetch" \
--tag "${repo}:${IMAGE_TAG}" \
--tag "${repo}:latest" \
-f "${REPO_ROOT}/server/Dockerfile" \
"${REPO_ROOT}/server"
;;
tenant-api|worker-generate|kol-assist-worker|scheduler|ops-api)
docker build "${platform_args[@]}" \
--target runtime \
+3 -1
View File
@@ -59,7 +59,7 @@ cd "${REPO_ROOT}"
if [[ -n "${SOURCE_IMAGE_REGISTRY}" ]]; then
echo " pulling from ${SOURCE_IMAGE_REGISTRY}"
for svc in tenant-api worker-generate kol-assist-worker ops-api scheduler migrate frontend ops-web; do
for svc in tenant-api browser-fetch worker-generate kol-assist-worker ops-api scheduler migrate frontend ops-web; do
echo " pulling ${SOURCE_IMAGE_REGISTRY}/${svc}:${IMAGE_TAG}"
docker pull --platform "${PLATFORM}" "${SOURCE_IMAGE_REGISTRY}/${svc}:${IMAGE_TAG}"
docker tag "${SOURCE_IMAGE_REGISTRY}/${svc}:${IMAGE_TAG}" "${LOCAL_PREFIX}/${svc}:${IMAGE_TAG}"
@@ -81,6 +81,7 @@ else
}
_build runtime tenant-api --build-arg SERVICE=tenant-api
_build browser-fetch browser-fetch --build-arg SERVICE=browser-fetch
_build runtime worker-generate --build-arg SERVICE=worker-generate
_build runtime kol-assist-worker --build-arg SERVICE=kol-assist-worker
_build runtime ops-api --build-arg SERVICE=ops-api
@@ -127,6 +128,7 @@ mkdir -p "${WORK_DIR}"
ALL_IMAGES=(
"${LOCAL_PREFIX}/tenant-api:${IMAGE_TAG}"
"${LOCAL_PREFIX}/browser-fetch:${IMAGE_TAG}"
"${LOCAL_PREFIX}/worker-generate:${IMAGE_TAG}"
"${LOCAL_PREFIX}/kol-assist-worker:${IMAGE_TAG}"
"${LOCAL_PREFIX}/scheduler:${IMAGE_TAG}"