fix(ci): authenticate the nightly dependency-bump API calls (#11042)

The "Bump Backend dependencies" workflow has failed every night for the
last two weeks. #11012 fixed one cause (repos renamed under localai-org);
what is left is rate limiting.

bump_deps.sh fans out to ~25 parallel matrix jobs that each query
api.github.com anonymously. Anonymous calls are capped at 60/hour per
source IP and GitHub-hosted runners egress through shared NAT addresses,
so a random handful of jobs draw HTTP 403 and die at curl exit 22 with an
empty response. Last night that hit ggml-org/whisper.cpp and
mudler/depth-anything.cpp -- both public and resolvable, nothing wrong
with either pin.

Route every bump script through a shared gh_curl helper that sends
GITHUB_TOKEN when present (1000/hour instead of 60) and retries transient
failures, including the 403s that plain --retry ignores. The helper
suppresses xtrace around the call so the Authorization header cannot land
in a public job log.

bump_docs.sh had a sharper version of the same bug: it piped an
unchecked response into `jq -r .tag_name`, so a throttled request
resolved to the string "null" and would have been published as the docs
version. It now refuses to write anything it cannot resolve to a tag.

Verified locally by running all four scripts end to end against their
real upstreams: correct SHAs/tags written, exit 0; a nonexistent repo now
fails with a named diagnostic instead of a bare exit 22 and leaves the
pinned file untouched; the token is absent from the xtrace output; and
the scripts still work unauthenticated.

Assisted-by: Claude:opus-4.8 [Claude Code]

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

.github/bump_deps.sh

@@ -1,5 +1,8 @@
 #!/bin/bash
 set -xe
+
+source "$(dirname "${BASH_SOURCE[0]}")/gh_curl.sh"
+
 REPO=$1
 BRANCH=$2
 VAR=$3
@@ -9,10 +12,11 @@ if [ -z "$FILE" ]; then
     FILE="Makefile"
 fi
 
-# -L so a renamed/transferred upstream repo (GitHub answers 301) still
-# resolves instead of handing us the redirect body, and -f so an HTTP error
-# aborts the run rather than letting an error page reach sed below.
-LAST_COMMIT=$(curl -sfL -H "Accept: application/vnd.github.VERSION.sha" "https://api.github.com/repos/$REPO/commits/$BRANCH")
+# gh_curl follows redirects so a renamed/transferred upstream repo (GitHub
+# answers 301) still resolves, and fails on HTTP errors rather than letting an
+# error page reach sed below. `|| true` keeps a failed lookup from aborting the
+# script at exit 22 with no context — the SHA guard below reports it instead.
+LAST_COMMIT=$(gh_curl -H "Accept: application/vnd.github.VERSION.sha" "https://api.github.com/repos/$REPO/commits/$BRANCH" || true)
 
 # Guard the sed input: anything that is not a bare 40-hex SHA (an API error
 # body, an empty response) would otherwise be spliced into the Makefile pin —

.github/bump_docs.sh

@@ -1,7 +1,18 @@
 #!/bin/bash
 set -xe
+
+source "$(dirname "${BASH_SOURCE[0]}")/gh_curl.sh"
+
 REPO=$1
 
-LATEST_TAG=$(curl -s "https://api.github.com/repos/$REPO/releases/latest" | jq -r '.tag_name')
+LATEST_TAG=$(gh_curl -H "Accept: application/vnd.github+json" \
+    "https://api.github.com/repos/$REPO/releases/latest" | jq -r '.tag_name')
+
+# jq prints the string "null" for a missing key, so a throttled or otherwise
+# unexpected API response would otherwise be published as the docs version.
+if [ -z "$LATEST_TAG" ] || [ "$LATEST_TAG" = "null" ]; then
+    echo "Refusing to bump docs version: could not resolve the latest release tag for $REPO." >&2
+    exit 1
+fi
 
 cat <<< $(jq ".version = \"$LATEST_TAG\"" docs/data/version.json) > docs/data/version.json

.github/bump_vllm_metal.sh

@@ -11,6 +11,9 @@
 # darwin build can only use the exact vLLM version vllm-metal supports, so it may
 # lag the Linux pin (requirements-cublas13-after.txt) until vllm-metal catches up.
 set -xe
+
+source "$(dirname "${BASH_SOURCE[0]}")/gh_curl.sh"
+
 REPO=$1   # vllm-project/vllm-metal
 FILE=$2   # backend/python/vllm/install.sh
 VAR=$3    # VLLM_METAL_VERSION (used for the workflow's output file names)
@@ -22,12 +25,12 @@ fi
 
 # vllm-metal ships frequent dev releases, all flagged as non-prerelease, so
 # /releases/latest returns the newest one (with its cp312 wheel asset).
-LATEST_TAG=$(curl -sS -H "Accept: application/vnd.github+json" \
+LATEST_TAG=$(gh_curl -H "Accept: application/vnd.github+json" \
     "https://api.github.com/repos/$REPO/releases/latest" \
     | python3 -c "import json,sys; print(json.load(sys.stdin)['tag_name'])")
 
 # The coupled vLLM source version lives in vllm-metal's installer at that tag.
-NEW_VLLM_VERSION=$(curl -fsSL \
+NEW_VLLM_VERSION=$(gh_curl \
     "https://raw.githubusercontent.com/$REPO/$LATEST_TAG/install.sh" \
     | grep -oE 'vllm_v="[0-9]+\.[0-9]+\.[0-9]+"' | head -1 | cut -d'"' -f2)
 

.github/bump_vllm_wheel.sh

@@ -9,6 +9,9 @@
 # vars in Makefiles; this script handles the two-value rewrite specific to the
 # vLLM requirements file.
 set -xe
+
+source "$(dirname "${BASH_SOURCE[0]}")/gh_curl.sh"
+
 REPO=$1   # vllm-project/vllm
 FILE=$2   # backend/python/vllm/requirements-cublas13-after.txt
 VAR=$3    # VLLM_VERSION (used for output file names so the workflow can read them)
@@ -19,7 +22,7 @@ if [ -z "$FILE" ] || [ -z "$REPO" ] || [ -z "$VAR" ]; then
 fi
 
 # /releases/latest returns the most recent non-prerelease tag.
-LATEST_TAG=$(curl -sS -H "Accept: application/vnd.github+json" \
+LATEST_TAG=$(gh_curl -H "Accept: application/vnd.github+json" \
     "https://api.github.com/repos/$REPO/releases/latest" \
     | python3 -c "import json,sys; print(json.load(sys.stdin)['tag_name'])")
 

.github/gh_curl.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+# Shared curl wrapper for the nightly dependency-bump scripts.
+#
+# The bump workflow fans out to ~25 parallel matrix jobs, each querying
+# api.github.com. Anonymous API calls are capped at 60/hour per source IP and
+# GitHub-hosted runners egress through shared NAT addresses, so a random handful
+# of jobs were getting rate-limited (HTTP 403 -> curl exit 22, empty response)
+# every single night. Authenticating with GITHUB_TOKEN lifts the ceiling to
+# 1000/hour; the retries absorb whatever transient blips remain.
+
+# Wraps curl with GitHub auth (when a token is present) plus retry/timeout
+# hardening. Callers pass their own headers and the URL.
+gh_curl() {
+    # The bump scripts run under `set -x`; without this the Authorization header
+    # would be echoed into the job log on every call.
+    local had_xtrace=0
+    case "$-" in
+        *x*) had_xtrace=1; set +x ;;
+    esac
+
+    local args=(
+        --silent --show-error --location --fail
+        # --retry-all-errors so 403 rate-limit responses are retried too; plain
+        # --retry only covers 408/429/5xx. curl honours Retry-After when sent.
+        --retry 5 --retry-delay 3 --retry-all-errors
+        --connect-timeout 15 --max-time 60
+    )
+    if [ -n "${GITHUB_TOKEN:-}" ]; then
+        args+=(--header "Authorization: Bearer ${GITHUB_TOKEN}")
+    fi
+
+    curl "${args[@]}" "$@"
+    local rc=$?
+
+    if [ "$had_xtrace" -eq 1 ]; then
+        set -x
+    fi
+    return $rc
+}

.github/workflows/bump_deps.yaml

@@ -115,6 +115,12 @@ jobs:
       - uses: actions/checkout@v7
       - name: Bump dependencies 🔧
         id: bump
+        env:
+          # This job fans out to ~25 parallel matrix entries, all querying
+          # api.github.com from runner IPs that share the 60/hour anonymous
+          # rate limit. Authenticating raises it to 1000/hour, which is what
+          # kept a random handful of these red every night.
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           bash .github/bump_deps.sh ${{ matrix.repository }} ${{ matrix.branch }} ${{ matrix.variable }} ${{ matrix.file }}
           {
@@ -151,6 +157,8 @@ jobs:
       - uses: actions/checkout@v7
       - name: Bump vLLM cu130 wheel pin 🔧
         id: bump
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           bash .github/bump_vllm_wheel.sh vllm-project/vllm backend/python/vllm/requirements-cublas13-after.txt VLLM_VERSION
           {
@@ -187,6 +195,8 @@ jobs:
       - uses: actions/checkout@v7
       - name: Bump vllm-metal pin 🔧
         id: bump
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           bash .github/bump_vllm_metal.sh vllm-project/vllm-metal backend/python/vllm/install.sh VLLM_METAL_VERSION
           {

.github/workflows/bump_docs.yaml

@@ -15,6 +15,10 @@ jobs:
     steps:
       - uses: actions/checkout@v7
       - name: Bump dependencies 🔧
+        env:
+          # Authenticated API calls get 1000 req/hour instead of the 60/hour
+          # anonymous cap that is shared across every job on the runner's IP.
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           bash .github/bump_docs.sh ${{ matrix.repository }}
       - name: Create Pull Request