proto becomes bxcore, the one shared crate (M5b task 00)

Done the way the owner asked and the spike mapped: the crate and the
manifests renamed, then what the build reported fixed. Layers: 138
"proto unresolved" errors across 169 files; cargo fmt reordering
imports; six fixture paths built as strings in brokerd's and bxctl's
tests, which the compiler cannot see, and comments naming
crates/proto/; the crate-dependency check and its self-test. One more
the spike did not reach: a `\nproto =` key inside a printf format in
the self-test, which a word-boundary replacement skips because `n` and
`p` are both word characters.

make gate: gate: ok, 944 tests; no new entry in /tmp.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

crates/loopd/tests/broker_port.rs

@@ -9,12 +9,12 @@ use std::os::unix::net::UnixListener;
 use std::thread;
 use std::time::Duration;
 
+use bxcore::{
+    DenyReason, Message, PROTOCOL_VERSION, Timestamp, ToolResponse, read_frame, write_frame,
+};
 use fake::{assert_unavailable, broker, call, frame, in_ms, request, result, send, socket_path};
 use loopd::broker_port::{BrokerPort, NoBroker, POINTER, TOO_LARGE};
 use loopd::tools::{Pending, ToolPort};
-use proto::{
-    DenyReason, Message, PROTOCOL_VERSION, Timestamp, ToolResponse, read_frame, write_frame,
-};
 
 #[test]
 fn a_result_comes_back_as_it_was_sent() {
@@ -259,7 +259,7 @@ fn a_request_too_large_for_a_frame_is_its_own_failure() {
     let _ = std::fs::remove_file(&path);
     let _listener = UnixListener::bind(&path).unwrap();
     let mut big = request();
-    big.arguments = format!(r#"{{"path":"/{}"}}"#, "a".repeat(proto::MAX_FRAME));
+    big.arguments = format!(r#"{{"path":"/{}"}}"#, "a".repeat(bxcore::MAX_FRAME));
     let got = call(path.to_path_buf(), 1_000, &big);
     assert_eq!(
         got.response,