Parser consumes stream directly, yields tool calls via channel

ResponseParser::run() spawns a task that reads StreamTokens, parses
into the AST (locking context per token), and sends PendingToolCalls
through a channel. Returns (tool_rx, JoinHandle<Result>) — the turn
loop dispatches tool calls and awaits the handle for error checking.

Token IDs from vLLM are accumulated alongside text and stored directly
on AST leaves — no local re-encoding on the response path.

The turn loop no longer matches on individual stream events. It just
reads tool calls and dispatches them.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>

src/agent/api/mod.rs

@@ -8,14 +8,13 @@
 
 pub mod http;
 
-use anyhow::Result;
 use std::time::{Duration, Instant};
-
-use self::http::{HttpClient, HttpResponse};
-
+use anyhow::Result;
 use tokio::sync::mpsc;
 use serde::Deserialize;
 
+use http::{HttpClient, HttpResponse};
+
 #[derive(Debug, Clone, Deserialize)]
 pub struct Usage {
     pub prompt_tokens: u32,