vector: build weed-vector without a system protoc (#12317)

* vector: build without a system protoc

lance's build scripts run $PROTOC and fail without one. Point it at the
protoc that protoc-bin-vendored ships, at the version in Cargo.lock, so
building inside seaweed-vector/ needs only the Rust toolchain. An explicit
PROTOC still wins, and a registry without the crate falls back to PATH.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK

* test(s3vectors): build weed-vector inside its workspace

Cargo reads seaweed-vector/.cargo/config.toml only when it runs there, so
build from that directory to pick up the vendored protoc.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK

* ci(vector): drop the PROTOC step the workspace config replaces

Builds run inside seaweed-vector/, where the cargo config already points
lance at the vendored protoc.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK

* test(s3vectors): resolve CARGO_TARGET_DIR before changing directory

A relative CARGO_TARGET_DIR given to make would point cargo, which now runs
in seaweed-vector/, and the cp after it at different directories.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK

* vector: pick the vendored protoc on every Linux host it ships for

protoc-bin-vendored also carries ppc64le, s390x and x86_32 binaries.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

.github/workflows/rust-vector-tests.yml

@@ -68,19 +68,6 @@ jobs:
           restore-keys: |
             rust-vector-${{ steps.toolchain.outputs.fingerprint }}-
 
-      # lance's build scripts compile their own protos and look for a protoc.
-      # Point them at the one protoc-bin-vendored ships, so no job depends on a
-      # system package and every build sees the same version.
-      - name: Use the vendored protoc
-        run: |
-          cd seaweed-vector
-          cargo fetch
-          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
-          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
-          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
-          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
-          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
-
       - name: Build the vector crates
         run: cd seaweed-vector && cargo build --release
 
@@ -125,15 +112,6 @@ jobs:
           key: vectors-e2e-${{ runner.os }}-${{ runner.arch }}-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-vector/Cargo.lock', 'seaweed-volume/Cargo.lock') }}
           restore-keys: |
             vectors-e2e-${{ runner.os }}-${{ runner.arch }}-${{ steps.toolchain.outputs.fingerprint }}-
-      - name: Use the vendored protoc
-        run: |
-          cd seaweed-vector
-          cargo fetch
-          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
-          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
-          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
-          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
-          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
       - name: Test Go vector gateway
         run: |
           go test ./weed/s3api/s3vectors -count=1

seaweed-vector/.cargo/config.toml

@@ -0,0 +1,6 @@
+# lance's build scripts run $PROTOC. Point them at the protoc that
+# protoc-bin-vendored ships, as this workspace's own build script does, so a
+# build needs no system protoc. An explicit PROTOC still wins. Cargo reads this
+# file only when it runs inside seaweed-vector/.
+[env]
+PROTOC = { value = ".cargo/protoc", relative = true }

seaweed-vector/.cargo/protoc

@@ -0,0 +1,21 @@
+#!/bin/sh
+# Runs the protoc of the protoc-bin-vendored version in Cargo.lock, or the one
+# on PATH when the registry does not hold it.
+case "$(uname -s)-$(uname -m)" in
+Linux-x86_64) platform=linux-x86_64 ;;
+Linux-aarch64) platform=linux-aarch_64 ;;
+Linux-ppc64le) platform=linux-ppcle_64 ;;
+Linux-s390x) platform=linux-s390_64 ;;
+Linux-i?86) platform=linux-x86_32 ;;
+Darwin-x86_64) platform=macos-x86_64 ;;
+Darwin-arm64) platform=macos-aarch_64 ;;
+*) exec protoc "$@" ;;
+esac
+crate="protoc-bin-vendored-$platform"
+version=$(awk -v name="\"$crate\"" '$1 == "name" && $3 == name { found = 1; next } found && $1 == "version" { gsub(/"/, "", $3); print $3; exit }' "$(dirname "$0")/../Cargo.lock")
+for protoc in "${CARGO_HOME:-$HOME/.cargo}"/registry/src/*/"$crate-$version"/bin/protoc; do
+	if [ -x "$protoc" ]; then
+		exec "$protoc" "$@"
+	fi
+done
+exec protoc "$@"

test/s3vectors/Makefile

@@ -7,6 +7,7 @@ endif
 VOLUME := ./weed-volume
 CARGO_PROFILE ?= release
 CARGO_TARGET_DIR ?= $(abspath ../../seaweed-vector/target)
+override CARGO_TARGET_DIR := $(abspath $(CARGO_TARGET_DIR))
 CARGO_OUTPUT := $(CARGO_TARGET_DIR)/$(if $(filter dev,$(CARGO_PROFILE)),debug,$(CARGO_PROFILE))
 export CARGO_TARGET_DIR
 
@@ -18,7 +19,7 @@ $(WEED): FORCE
 	go build -o $(WEED) ../../weed
 
 $(VEC): FORCE
-	cargo build --locked --profile $(CARGO_PROFILE) --manifest-path ../../seaweed-vector/Cargo.toml -p weed-vector-server
+	cd ../../seaweed-vector && cargo build --locked --profile $(CARGO_PROFILE) -p weed-vector-server
 	cp $(CARGO_OUTPUT)/weed-vector $(VEC)
 
 ifneq ($(WORKER),)