feat: stream Reginald's replies token-by-token

The 26b is slow (~30s/call); the chat now shows the answer forming instead of
freezing until it's done. The final prose streams over SSE; tool-calling turns
stay structured (no partial tokens), so streaming kicks in for the narration.

core (@commitea/core):
- chat-client.complete gains an optional onToken — when set, it requests
  stream:true and parses the OpenAI SSE stream, emitting content deltas and
  assembling streamed tool-call argument fragments into the final result.
- GiteaHttpResponse exposes the optional `body` stream (real fetch has it; stubs
  don't). agent-loop threads onToken to each completion.

app:
- model:chat forwards each delta to the renderer (event.sender.send); preload
  exposes model.onToken(cb) → unsubscribe. useChat accumulates the live stream
  into a growing bubble (with a cursor), replaced by the authoritative final
  content when the turn resolves. Unconfigured → scripted reply, unchanged.

Verified: 118 core tests green (2 streaming: SSE content deltas + tool-call
fragment assembly), desktop typecheck clean, 14 fixture e2e green. Live: a real
turn against gemma-4-26b assembles the correct answer via the streaming path
(live-reginald green) — the reply now renders token-by-token.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

packages/core/src/agent/agent-loop.ts

@@ -31,18 +31,20 @@ function stringify(result: unknown): string {
 }
 
 export async function runAgentTurn(opts: {
-  complete: (messages: ChatMessage[], tools?: ToolDecl[]) => Promise<CompletionResult>
+  complete: (messages: ChatMessage[], tools?: ToolDecl[], onToken?: (delta: string) => void) => Promise<CompletionResult>
   messages: ChatMessage[]
   tools: ToolDecl[]
   execute: ToolExecutor
   maxSteps?: number
+  /** Streams content deltas as the model produces prose (final-answer streaming). */
+  onToken?: (delta: string) => void
 }): Promise<AgentTurn> {
   const maxSteps = opts.maxSteps ?? DEFAULT_MAX_STEPS
   const convo: ChatMessage[] = [...opts.messages]
   const steps: AgentStep[] = []
 
   for (let step = 0; step < maxSteps; step++) {
-    const { content, toolCalls } = await opts.complete(convo, opts.tools)
+    const { content, toolCalls } = await opts.complete(convo, opts.tools, opts.onToken)
     if (toolCalls.length === 0) {
       convo.push({ role: 'assistant', content })
       return { content, steps, messages: convo }
@@ -63,7 +65,7 @@ export async function runAgentTurn(opts: {
   }
 
   // Out of tool budget — force a final prose answer with tools withheld.
-  const final = await opts.complete(convo, [])
+  const final = await opts.complete(convo, [], opts.onToken)
   convo.push({ role: 'assistant', content: final.content })
   return { content: final.content, steps, messages: convo }
 }