feat(graph): thread the graph abort into llm nodes and tool execution

LlmNodeExecutor::execute now takes the graph's abort signal and threads
it through run -> run_with_retries -> run_chat_loop, replacing the
loop-private signal, so an in-flight model call is interrupted and every
turn starts with an abort check that bails 'llm node aborted' before any
client is created.

run_llm_function gains an optional abort signal: the synchronous tool
wait loop kills the child and returns a 'Tool call ... aborted' error
within one poll interval when it is set. The tool dispatcher passes the
session abort; the agent _instructions runner passes None.

src/graph/executor.rs

@@ -580,7 +580,9 @@ pub(super) async fn step(
             Ok(StepResult::Continue(vec![next]))
         }
         NodeType::Llm(llm_node) => {
-            let outcome = LlmNodeExecutor::execute(current, llm_node, state, ctx).await?;
+            let outcome =
+                LlmNodeExecutor::execute(current, llm_node, state, ctx, step_ctx.abort_signal)
+                    .await?;
             let targets = match outcome {
                 LlmExecutionOutcome::Continue => {
                     static_next_targets(node, current, "llm", step_ctx.branch_mode)?