fix(docker): entrypoint shim so child images with custom CMD work (#28)

v0.3.13 switched ENTRYPOINT to ["webclaw"] to make `docker run IMAGE
https://example.com` work. That broke a different use case: downstream
Dockerfiles that `FROM ghcr.io/0xmassi/webclaw` and set their own
CMD ["./setup.sh"] — the child's ./setup.sh becomes arg to webclaw,
which tries to fetch it as a URL and fails:

  fetch error: request failed: error sending request for uri
  (https://./setup.sh): client error (Connect)

Both Dockerfile and Dockerfile.ci now use docker-entrypoint.sh which:
- forwards flags (-*) and URLs (http://, https://) to `webclaw`
- exec's anything else directly

Test matrix (all pass locally):
  docker run IMAGE https://example.com     → webclaw scrape ok
  docker run IMAGE --help                   → webclaw --help ok
  docker run IMAGE                          → default CMD, --help
  docker run IMAGE bash                     → bash runs
  FROM IMAGE + CMD ["./setup.sh"]           → setup.sh runs, webclaw available

Default CMD is ["webclaw", "--help"] so bare `docker run IMAGE` still
prints help.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

CHANGELOG.md

@@ -3,6 +3,13 @@
 All notable changes to webclaw are documented here.
 Format follows [Keep a Changelog](https://keepachangelog.com/).
 
+## [0.3.19] — 2026-04-17
+
+### Fixed
+- **Docker image can be used as a FROM base again.** v0.3.13 switched the Docker `CMD` to `ENTRYPOINT ["webclaw"]` so that `docker run IMAGE https://example.com` would pass the URL through as expected. That change trapped a different use case: downstream Dockerfiles that `FROM ghcr.io/0xmassi/webclaw` and set their own `CMD ["./setup.sh"]` — the child's `./setup.sh` became the first arg to `webclaw`, which tried to fetch it as a URL and failed with `error sending request for uri (https://./setup.sh)`. Both `Dockerfile` and `Dockerfile.ci` now use a small `docker-entrypoint.sh` shim that forwards flags (`-*`) and URLs (`http://`, `https://`) to `webclaw`, but `exec`s anything else directly. All four use cases now work: `docker run IMAGE https://example.com`, `docker run IMAGE --help`, child-image `CMD ["./setup.sh"]`, and `docker run IMAGE bash` for debugging. Default `CMD` is `["webclaw", "--help"]`.
+
+---
+
 ## [0.3.18] — 2026-04-16
 
 ### Fixed

Cargo.lock

@@ -3102,7 +3102,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-cli"
-version = "0.3.18"
+version = "0.3.19"
 dependencies = [
  "clap",
  "dotenvy",
@@ -3123,7 +3123,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-core"
-version = "0.3.18"
+version = "0.3.19"
 dependencies = [
  "ego-tree",
  "once_cell",
@@ -3141,7 +3141,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-fetch"
-version = "0.3.18"
+version = "0.3.19"
 dependencies = [
  "bytes",
  "calamine",
@@ -3163,7 +3163,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-llm"
-version = "0.3.18"
+version = "0.3.19"
 dependencies = [
  "async-trait",
  "reqwest",
@@ -3176,7 +3176,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-mcp"
-version = "0.3.18"
+version = "0.3.19"
 dependencies = [
  "dirs",
  "dotenvy",
@@ -3197,7 +3197,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-pdf"
-version = "0.3.18"
+version = "0.3.19"
 dependencies = [
  "pdf-extract",
  "thiserror",

Cargo.toml

@@ -3,7 +3,7 @@ resolver = "2"
 members = ["crates/*"]
 
 [workspace.package]
-version = "0.3.18"
+version = "0.3.19"
 edition = "2024"
 license = "AGPL-3.0"
 repository = "https://github.com/0xMassi/webclaw"

Dockerfile

@@ -58,5 +58,10 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY --from=builder /build/target/release/webclaw /usr/local/bin/webclaw
 COPY --from=builder /build/target/release/webclaw-mcp /usr/local/bin/webclaw-mcp
 
-# Default: run the CLI (ENTRYPOINT so args pass through)
-ENTRYPOINT ["webclaw"]
+# Entrypoint shim: forwards webclaw args/URL to the binary, but exec's other
+# commands directly so this image can be used as a FROM base with custom CMD.
+COPY docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+
+ENTRYPOINT ["docker-entrypoint.sh"]
+CMD ["webclaw", "--help"]

Dockerfile.ci

@@ -13,4 +13,10 @@ ARG BINARY_DIR
 COPY ${BINARY_DIR}/webclaw /usr/local/bin/webclaw
 COPY ${BINARY_DIR}/webclaw-mcp /usr/local/bin/webclaw-mcp
 
-ENTRYPOINT ["webclaw"]
+# Entrypoint shim: forwards webclaw args/URL to the binary, but exec's other
+# commands directly so this image can be used as a FROM base with custom CMD.
+COPY docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+
+ENTRYPOINT ["docker-entrypoint.sh"]
+CMD ["webclaw", "--help"]

docker-entrypoint.sh

@@ -0,0 +1,33 @@
+#!/bin/sh
+# webclaw docker entrypoint.
+#
+# Behaves like the real binary when the first arg looks like a webclaw arg
+# (URL or flag), so `docker run ghcr.io/0xmassi/webclaw https://example.com`
+# still works. But gets out of the way when the first arg looks like a
+# different command (e.g. `./setup.sh`, `bash`, `sh -c ...`), so this image
+# can be used as a FROM base in downstream Dockerfiles with a custom CMD.
+#
+# Test matrix:
+#   docker run IMAGE https://example.com          → webclaw https://example.com
+#   docker run IMAGE --help                       → webclaw --help
+#   docker run IMAGE --file page.html             → webclaw --file page.html
+#   docker run IMAGE --stdin < page.html          → webclaw --stdin
+#   docker run IMAGE bash                         → bash
+#   docker run IMAGE ./setup.sh                   → ./setup.sh
+#   docker run IMAGE                              → webclaw --help (default CMD)
+#
+# Root cause fixed: v0.3.13 switched CMD→ENTRYPOINT to make the first use
+# case work, which trapped the last four. This shim restores all of them.
+
+set -e
+
+# If the first arg starts with `-`, `http://`, or `https://`, treat the
+# whole arg list as webclaw flags/URL.
+if [ "$#" -gt 0 ] && {
+    [ "${1#-}" != "$1" ] || \
+    [ "${1#http://}" != "$1" ] || \
+    [ "${1#https://}" != "$1" ]; }; then
+    set -- webclaw "$@"
+fi
+
+exec "$@"