Add GitHub API caching to prevent rate limiting

.devcontainer/Dockerfile

@@ -69,10 +69,10 @@ RUN sh -c "$(wget -O- https://github.com/deluan/zsh-in-docker/releases/download/
 # Install Claude
 RUN npm install -g @anthropic-ai/claude-code
 
-# Copy and set up firewall script
-COPY init-firewall.sh /usr/local/bin/
+# Copy and set up scripts
+COPY init-firewall.sh cache-github-api.sh /usr/local/bin/
 USER root
-RUN chmod +x /usr/local/bin/init-firewall.sh && \
+RUN chmod +x /usr/local/bin/init-firewall.sh /usr/local/bin/cache-github-api.sh && \
   echo "node ALL=(root) NOPASSWD: /usr/local/bin/init-firewall.sh" > /etc/sudoers.d/node-firewall && \
   chmod 0440 /etc/sudoers.d/node-firewall
 USER node

.devcontainer/cache-github-api.sh

@@ -0,0 +1,109 @@
+#!/bin/bash
+set -e
+
+# Script to cache GitHub API data
+# Used to prevent rate limiting during container builds
+
+# Configuration
+# Store cache in the home directory
+CACHE_DIR="${HOME}/.github-meta-cache"
+CACHE_FILE="${CACHE_DIR}/meta.json"
+TIMESTAMP_FILE="${CACHE_DIR}/meta-timestamp.txt"
+MAX_AGE_SECONDS=3600  # Cache expires after 1 hour
+
+# Create cache directory if it doesn't exist
+mkdir -p "${CACHE_DIR}"
+
+# Function to get current timestamp
+get_timestamp() {
+  date +%s
+}
+
+# Function to check if cache is valid
+is_cache_valid() {
+  if [[ ! -f "${CACHE_FILE}" || ! -f "${TIMESTAMP_FILE}" ]]; then
+    return 1
+  fi
+
+  local cache_time=$(cat "${TIMESTAMP_FILE}")
+  local current_time=$(get_timestamp)
+  local age=$((current_time - cache_time))
+
+  if [[ ${age} -gt ${MAX_AGE_SECONDS} ]]; then
+    echo "Cache is expired (${age} seconds old)"
+    return 1
+  fi
+
+  echo "Using cached GitHub API data (${age} seconds old)"
+  return 0
+}
+
+# Function to fetch data using authenticated gh cli
+fetch_with_gh() {
+  echo "Attempting to fetch GitHub API data using authenticated gh CLI..."
+  if gh auth status &>/dev/null; then
+    gh api meta > "${CACHE_FILE}" && 
+      get_timestamp > "${TIMESTAMP_FILE}" &&
+      echo "Successfully fetched and cached GitHub API data using gh CLI"
+    return $?
+  else
+    echo "gh CLI not authenticated"
+    return 1
+  fi
+}
+
+# Function to fetch data using curl
+fetch_with_curl() {
+  echo "Attempting to fetch GitHub API data using curl..."
+  # First try with GITHUB_TOKEN if available
+  if [[ -n "${GITHUB_TOKEN}" ]]; then
+    echo "Using GITHUB_TOKEN for authentication"
+    curl -s -H "Authorization: token ${GITHUB_TOKEN}" https://api.github.com/meta > "${CACHE_FILE}" &&
+      get_timestamp > "${TIMESTAMP_FILE}" &&
+      echo "Successfully fetched and cached GitHub API data using curl with token"
+    return $?
+  else
+    # Fall back to unauthenticated request
+    echo "No GITHUB_TOKEN found, making unauthenticated request (may be rate limited)"
+    curl -s https://api.github.com/meta > "${CACHE_FILE}"
+
+    # Check if the response indicates rate limiting
+    if grep -q "API rate limit exceeded" "${CACHE_FILE}"; then
+      echo "Rate limit exceeded for unauthenticated request"
+      return 1
+    else
+      get_timestamp > "${TIMESTAMP_FILE}"
+      echo "Successfully fetched and cached GitHub API data using curl without auth"
+      return 0
+    fi
+  fi
+}
+
+# Main logic
+if is_cache_valid; then
+  echo "Using existing cache from $(cat ${TIMESTAMP_FILE})"
+  exit 0
+fi
+
+# Try with gh CLI first
+if ! fetch_with_gh; then
+  # Fall back to curl
+  if ! fetch_with_curl; then
+    # Both methods failed, check if we have an existing cache file
+    if [[ -f "${CACHE_FILE}" ]]; then
+      echo "Warning: Failed to update cache, using existing cached data (which may be expired)"
+      exit 0
+    else
+      echo "Error: Failed to fetch GitHub API data and no cache exists"
+      exit 1
+    fi
+  fi
+fi
+
+# Display a summary of the cached data
+echo "GitHub API meta data cached successfully. Summary:"
+jq -r '.domains.actions | length' "${CACHE_FILE}" > /dev/null 2>&1 && 
+  echo "- Actions domains: $(jq -r '.domains.actions | length' "${CACHE_FILE}")" ||
+  echo "- Could not parse actions domains from cache file"
+
+exit 0

.devcontainer/devcontainer.json

@@ -4,6 +4,9 @@
     "dockerfile": "Dockerfile",
     "args": {
       "TZ": "${localEnv:TZ:America/Los_Angeles}"
+    },
+    "prebuild": {
+      "command": "bash -c '${localWorkspaceFolder}/.devcontainer/cache-github-api.sh || echo \"Warning: Failed to cache GitHub API data\"'"
     }
   },
   "runArgs": [
@@ -39,7 +42,8 @@
   "remoteUser": "node",
   "mounts": [
     "source=claude-code-bashhistory,target=/commandhistory,type=volume",
-    "source=claude-code-config,target=/home/node/.claude,type=volume"
+    "source=claude-code-config,target=/home/node/.claude,type=volume", 
+    "type=bind,source=${localEnv:HOME}/.github-meta-cache,target=/github-meta-cache,consistency=cached"
   ],
   "remoteEnv": {
     "NODE_OPTIONS": "--max-old-space-size=4096",

.devcontainer/init-firewall.sh

@@ -27,16 +27,20 @@ iptables -A OUTPUT -o lo -j ACCEPT
 # Create ipset with CIDR support
 ipset create allowed-domains hash:net
 
-# Fetch GitHub meta information and aggregate + add their IP ranges
-echo "Fetching GitHub IP ranges..."
-gh_ranges=$(curl -s https://api.github.com/meta)
-if [ -z "$gh_ranges" ]; then
-    echo "ERROR: Failed to fetch GitHub IP ranges"
-    exit 1
-fi
+# Use cached GitHub meta information from mounted volume
+CACHE_FILE="/github-meta-cache/meta.json"
 
-if ! echo "$gh_ranges" | jq -e '.web and .api and .git' >/dev/null; then
-    echo "ERROR: GitHub API response missing required fields"
+echo "Using cached GitHub IP ranges..."
+if [ -f "${CACHE_FILE}" ]; then
+    gh_ranges=$(cat "${CACHE_FILE}")
+
+    # Verify the cached data is valid
+    if ! echo "$gh_ranges" | jq -e '.web and .api and .git' >/dev/null; then
+        echo "ERROR: Cached GitHub API data is invalid"
+        exit 1
+    fi
+else
+    echo "ERROR: No cached GitHub IP ranges found"
     exit 1
 fi