Stage 7a-i: TP worker lifecycle scaffolding

Leader → worker process plumbing for tensor parallelism. The neuron
binary picks up two modes: default (the existing daemon, axum + HTTP)
and `--worker` (a bare RPC loop driven over stdin/stdout). The leader
spawns one worker per non-zero NCCL rank via tokio::process::Command
on the same binary path (production: /proc/self/exe; tests:
env!("CARGO_BIN_EXE_neuron")) and talks to each over newline-
delimited JSON.

Protocol (harness/tp/rpc.rs) is serde-tagged from the start —
WorkerRequest::{Ping, Init, NcclSanityCheck, Shutdown} and
WorkerResponse::{Pong, InitOk, NcclSanityResult, Bye, Error}, both
`#[serde(tag = "op", rename_all = "snake_case")]`. Adding ops in 7b/7c
is purely additive; unknown ops on the wire fail to parse (verified
in unit tests).

7a-i scope:
- WorkerPool::spawn(binary, world_size, devices) forks ranks 1..N as
  subprocesses, captures stdin/stdout, kills on drop.
- ping_all() round-trips a Ping to every worker and validates the
  returned rank.
- shutdown() sends Shutdown to each worker, awaits Bye, reaps.
- Worker mode: parse Ping/Shutdown, return Pong/Bye; Init and
  NcclSanityCheck return Error{kind="not_implemented_7a_i"} so a 7a-ii
  binary speaking the same wire is a drop-in replacement (the kind
  field signals "real NCCL lands in the next commit").
- CandleHarness::load_model refuses tensor_parallel > 1 with a clear
  message until 7b is in.

Three integration tests in tests/tp_worker_lifecycle.rs cover spawn/
ping/shutdown for 2- and 3-worker pools, plus the
not_implemented_7a_i contract test for Init. Seven rpc serde unit
tests assert the wire shape (op tags, field names, unknown-op
rejection). All pass on the dev host; no CUDA required.

Stage 7a-ii (next): the real NCCL Comm::from_rank wiring behind the
existing Init/NcclSanityCheck op surface, CUDA-gated. Verifiable on
beast's 2×5090.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

crates/neuron/src/harness/candle.rs

@@ -404,6 +404,19 @@ impl Harness for CandleHarness {
             }
         }
 
+        // Stage 7a-i scaffolds tensor-parallel worker subprocesses but
+        // does not yet route inference through them. Refuse TP loads
+        // for now with a clear marker so the request surface is honest.
+        let tp_size = spec.tensor_parallel.unwrap_or(1);
+        if tp_size > 1 {
+            anyhow::bail!(
+                "tensor_parallel={tp_size} requested for '{}': TP worker \
+                 lifecycle is in place (Stage 7a-i) but TP-aware Qwen3 \
+                 inference lands in Stage 7b; single-GPU loads only for now",
+                spec.model_id
+            );
+        }
+
         let devices = spec.devices.clone().unwrap_or_else(|| vec![0]);
         let device = Self::pick_device(&devices)?;