From ebd3dcf3d8d1a5398169cfba464e372477e8396c Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Tue, 7 Jul 2026 21:08:05 +0000
Subject: [PATCH] fix(backends): pin grpcio-tools to the installed grpcio in
 runProtogen

runProtogen installed grpcio-tools unpinned, so the protoc it bundles
stamped backend_pb2.py with the newest Protobuf gencode (7.35.0). When a
backend caps the protobuf runtime lower -- vLLM pins protobuf to 6.33.6 --
the import-time guarantee runtime >= gencode fails:

  google.protobuf.runtime_version.VersionError: Detected incompatible
  Protobuf Gencode/Runtime versions ... gencode 7.35.0 runtime 6.33.6

The backend crashes on `import backend_pb2` before it can serve, which
surfaces to the user as "grpc service not ready". It was mis-reported as a
ROCm/gfx1201 failure in #10718 but is not GPU-specific and affects every
vLLM variant (and any backend that caps protobuf below the latest gencode).

Pin grpcio-tools to the grpcio version the backend already installed --
they release in lockstep -- so the generated gencode stays in step with
the protobuf runtime. Falls back to unpinned when grpcio isn't present.

Closes #10718

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
---
 backend/python/common/libbackend.sh | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/backend/python/common/libbackend.sh b/backend/python/common/libbackend.sh
index dc7517d06..b912f454f 100644
--- a/backend/python/common/libbackend.sh
+++ b/backend/python/common/libbackend.sh
@@ -397,10 +397,29 @@ function ensureVenv() {
 
 function runProtogen() {
     ensureVenv
+
+    # Match grpcio-tools to the grpcio already installed by the backend's
+    # requirements. grpcio and grpcio-tools are released in lockstep, and the
+    # protoc that grpcio-tools bundles stamps a Protobuf "gencode" version into
+    # backend_pb2.py. Left unpinned, `uv pip install grpcio-tools` pulls the
+    # newest release, whose newer gencode (e.g. 7.35.0) trips Protobuf's
+    # runtime >= gencode guarantee at import time when a backend caps the
+    # protobuf runtime lower (vLLM pins it to 6.33.6), crashing the backend with
+    # "grpc service not ready" before it ever loads a model. Pinning
+    # grpcio-tools to the installed grpcio version keeps the gencode in step with
+    # the runtime. Falls back to unpinned when grpcio isn't installed yet.
+    # See mudler/LocalAI#10718.
+    local grpcio_tools_spec="grpcio-tools"
+    local grpcio_version
+    grpcio_version="$(python -c 'import importlib.metadata as m; print(m.version("grpcio"))' 2>/dev/null || true)"
+    if [ -n "${grpcio_version}" ]; then
+        grpcio_tools_spec="grpcio-tools==${grpcio_version}"
+    fi
+
     if [ "x${USE_PIP}" == "xtrue" ]; then
-        pip install grpcio-tools
+        pip install "${grpcio_tools_spec}"
     else
-        uv pip install grpcio-tools
+        uv pip install "${grpcio_tools_spec}"
     fi
     pushd "${EDIR}" >/dev/null
         # use the venv python (ensures correct interpreter & sys.path)