Improve container build reliability (#457)

* docker: add .env usage in build-container.sh
* .github,docker: add rocm, improve logging
* .github,CLAUDE.md: fix workflow and update guidelines

Update containers workflow to only push images when triggered
manually or on schedule, not on workflow file changes.

- add push trigger for workflow file changes in containers.yml
- update push condition to skip on regular push events
- update CLAUDE.md commit message guidelines

* docker: remove comma in build-container.sh

* .github,docker: improve container build workflow

Add pagination support for fetching llama.cpp tags and improve debugging.

- add build-container.sh to workflow trigger paths
- implement fetch_llama_tag() with pagination support
- replace .env with local testing instructions
- add DEBUG_ABORT_BUILD flag for testing

.github/workflows/containers.yml

@@ -10,12 +10,18 @@ on:
   # Allows manual triggering of the workflow
   workflow_dispatch:
 
+  # Run on workflow file changes (without pushing)
+  push:
+    paths:
+      - '.github/workflows/containers.yml'
+      - 'docker/build-container.sh'
+
 jobs:
   build-and-push:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        platform: [intel, cuda, vulkan, cpu, musa]
+        platform: [intel, cuda, vulkan, cpu, musa, rocm]
       fail-fast: false
     steps:
       - name: Checkout code
@@ -31,7 +37,7 @@ jobs:
       - name: Run build-container
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: ./docker/build-container.sh ${{ matrix.platform }} true
+        run: ./docker/build-container.sh ${{ matrix.platform }} ${{ github.event_name != 'push' }}
 
   # note make sure mostlygeek/llama-swap has admin rights to the llama-swap package
   # see: https://github.com/actions/delete-package-versions/issues/74

CLAUDE.md

@@ -12,7 +12,7 @@ llama-swap is a light weight, transparent proxy server that provides automatic m
 - when summarizing changes only include details that require further action
 - just say "Done." when there is no further action
 - use `gh` to create PRs and load issues
-- do not mention "created by claude" in commit messages
+- do include Co-Authored-By or created by when committing changes or creating PRs
 - keep PR descriptions short and focused on changes.
   - never include a test plan
 

docker/build-container.sh

@@ -2,21 +2,37 @@
 
 cd $(dirname "$0")
 
+# use this to test locally, example:
+# GITHUB_TOKEN=$(gh auth token) LOG_DEBUG=1 DEBUG_ABORT_BUILD=1 ./docker/build-container.sh rocm
+# you need read:package scope on the token. Generate a personal access token with
+# the scopes: gist, read:org, repo, write:packages
+# then: gh auth login (and copy/paste the new token)
+
+log_debug() {
+    if [ "$LOG_DEBUG" = "1" ]; then
+        echo "[DEBUG] $*"
+    fi
+}
+
+log_info() {
+    echo "[INFO] $*"
+}
+
 ARCH=$1
 PUSH_IMAGES=${2:-false}
 
 # List of allowed architectures
-ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu")
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu" "rocm")
 
 # Check if ARCH is in the allowed list
 if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then
-  echo "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
+  log_info "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
   exit 1
 fi
 
 # Check if GITHUB_TOKEN is set and not empty
 if [[ -z "$GITHUB_TOKEN" ]]; then
-  echo "Error: GITHUB_TOKEN is not set or is empty."
+  log_info "Error: GITHUB_TOKEN is not set or is empty."
   exit 1
 fi
 
@@ -32,25 +48,74 @@ LS_REPO=${GITHUB_REPOSITORY:-mostlygeek/llama-swap}
 # have to strip out the 'v' due to .tar.gz file naming
 LS_VER=$(curl -s https://api.github.com/repos/${LS_REPO}/releases/latest | jq -r .tag_name | sed 's/v//')
 
+# Fetches the most recent llama.cpp tag matching the given prefix
+# Handles pagination to search beyond the first 100 results
+# $1 - tag_prefix (e.g., "server" or "server-vulkan")
+# Returns: the version number extracted from the tag
+fetch_llama_tag() {
+    local tag_prefix=$1
+    local page=1
+    local per_page=100
+
+    while true; do
+        log_debug "Fetching page $page for tag prefix: $tag_prefix"
+
+        local response=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+            "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions?per_page=${per_page}&page=${page}")
+
+        # Check for API errors
+        if echo "$response" | jq -e '.message' > /dev/null 2>&1; then
+            local error_msg=$(echo "$response" | jq -r '.message')
+            log_info "GitHub API error: $error_msg"
+            return 1
+        fi
+
+        # Check if response is empty array (no more pages)
+        if [ "$(echo "$response" | jq 'length')" -eq 0 ]; then
+            log_debug "No more pages (empty response)"
+            return 1
+        fi
+
+        # Extract matching tag from this page
+        local found_tag=$(echo "$response" | jq -r \
+            ".[] | select(.metadata.container.tags[]? | startswith(\"$tag_prefix\")) | .metadata.container.tags[] | select(startswith(\"$tag_prefix\"))" \
+            | sort -r | head -n1)
+
+        if [ -n "$found_tag" ]; then
+            log_debug "Found tag: $found_tag on page $page"
+            echo "$found_tag" | awk -F '-' '{print $NF}'
+            return 0
+        fi
+
+        page=$((page + 1))
+
+        # Safety limit to prevent infinite loops
+        if [ $page -gt 50 ]; then
+            log_info "Reached pagination safety limit (50 pages)"
+            return 1
+        fi
+    done
+}
+
 if [ "$ARCH" == "cpu" ]; then
-    # cpu only containers just use the server tag
+    LCPP_TAG=$(fetch_llama_tag "server")
-    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
-        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
-        | jq -r '.[] | select(.metadata.container.tags[] | startswith("server")) | .metadata.container.tags[]' \
-        | sort -r | head -n1 | awk -F '-' '{print $3}')
     BASE_TAG=server-${LCPP_TAG}
 else
-    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+    LCPP_TAG=$(fetch_llama_tag "server-${ARCH}")
-        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
-        | jq -r --arg arch "$ARCH" '.[] | select(.metadata.container.tags[] | startswith("server-\($arch)")) | .metadata.container.tags[]' \
-        | sort -r | head -n1 | awk -F '-' '{print $3}')
     BASE_TAG=server-${ARCH}-${LCPP_TAG}
 fi
 
 # Abort if LCPP_TAG is empty.
 if [[ -z "$LCPP_TAG" ]]; then
-    echo "Abort: Could not find llama-server container for arch: $ARCH"
+    log_info "Abort: Could not find llama-server container for arch: $ARCH"
     exit 1
+else
+    log_info "LCPP_TAG: $LCPP_TAG"
+fi
+
+if [[ ! -z "$DEBUG_ABORT_BUILD" ]]; then
+    log_info "Abort: DEBUG_ABORT_BUILD set"
+    exit 0
 fi
 
 for CONTAINER_TYPE in non-root root; do
@@ -68,7 +133,7 @@ for CONTAINER_TYPE in non-root root; do
     USER_HOME=/app
   fi
 
-  echo "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
+  log_info "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
   docker build -f llama-swap.Containerfile --build-arg BASE_TAG=${BASE_TAG} --build-arg LS_VER=${LS_VER} --build-arg UID=${USER_UID} \
     --build-arg LS_REPO=${LS_REPO} --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} \
     --build-arg BASE_IMAGE=${BASE_IMAGE} .