token streaming & reasoning display: live SSE tokens frontend to back

- Add StreamDelta(SseDecoder) framing shared by OpenAI/Anthropic
- OpenAiClient: stream=true + reasoning_content deltas, index-based
  tool_calls accumulation, usage from final chunk
- AnthropicClient: message_start/content_block_*/message_delta events,
  thinking_delta->reasoning, input_json_delta->tool input
- TokenDelta ServerEvent variant wired through ChatHub + WS broadcast
- Frontend throttled flush (~15 Hz), pending bubble mutate-in-place,
  reasoning as collapsed-by-default <details>
- Drop streaming bubble on error/llm_failed/model_fallback
- i18n: chat.reasoning key added to en/fr/it

crates/llm-client/Cargo.toml

@@ -5,9 +5,11 @@ edition = "2024"
 
 [dependencies]
 core-api    = { path = "../core-api" }
-reqwest     = { version = "0.13", default-features = false, features = ["rustls-no-provider", "charset", "http2", "system-proxy", "json"] }
+reqwest     = { version = "0.13", default-features = false, features = ["rustls-no-provider", "charset", "http2", "system-proxy", "json", "stream"] }
 serde       = { version = "1", features = ["derive"] }
 serde_json  = "1"
 async-trait = "0.1"
 anyhow      = "1"
 tracing     = "0.1"
+tokio       = { version = "1", features = ["sync"] }
+futures-util = "0.3"