feat: v0.5.16 - migrate to Responses API (#586)

* refactor: migrate from /v1/runs to /v1/responses streaming API

Replace EventSource-based polling with direct SSE streaming via the
/v1/responses endpoint across all server-side callers (chat-run-socket,
context-compressor, gateway-client, agent-clients). Messages are now
written to DB in real-time during streaming, eliminating post-run sync.
Frontend chat store adds tool_call_id tracking for deduplication.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* chore: bump version to 0.5.16 and add changelog

- Persist real API usage to usage table on response.completed
- Remove unused codex_reasoning_items field from message schema
- Fix unused variable warnings in chat-run-socket
- Bump version to 0.5.16
- Add changelog entries for 0.5.16 (8 locales)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

packages/client/src/i18n/locales/en.ts

@@ -912,6 +912,10 @@ export default {
     new_0_5_15_9: 'Fix Hermes markdown media rendering and sync retry',
     new_0_5_15_10: 'Refactor to remove upstream env dependency',
     new_0_5_15_11: 'If the Kanban feature is not available, please upgrade hermes-agent',
+    new_0_5_16_1: 'Migrate chat streaming from /v1/runs to /v1/responses API for lower latency',
+    new_0_5_16_2: 'Persist real API usage (tokens, cache, reasoning) to usage table',
+    new_0_5_16_3: 'Add QQ group QR code to website navigation bar',
+    new_0_5_16_4: 'Remove unused codex_reasoning_items field from message schema',
     new_0_5_13_1: 'Add message queue for sequential run processing to prevent concurrent request conflicts',
     new_0_5_13_2: 'Support two-level skills directory structure with misc category for flat skills',
     new_0_5_13_3: 'Filter out ephemeral sessions during startup sync to avoid importing internal sessions',