[claude] Add vllm-mlx as high-performance local inference backend (#1069) (#1089)

Co-authored-by: Claude (Opus 4.6) <claude@hermes.local> Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
2026-03-23 15:34:13 +00:00
parent 7fdd532260
commit f2a277f7b5
12 changed files with 350 additions and 77 deletions
--- a/tests/unit/test_kimi_delegation.py
+++ b/tests/unit/test_kimi_delegation.py
@@ -14,7 +14,6 @@ from timmy.kimi_delegation import (
    exceeds_local_capacity,
 )

-
 # ── Constants ─────────────────────────────────────────────────────────────────


@@ -455,9 +454,7 @@ class TestExtractAndCreateFollowups:
            patch("config.settings", mock_settings),
            patch("httpx.AsyncClient", return_value=async_ctx),
        ):
-            result = await extract_and_create_followups(
-                "1. Do the thing\n2. Do another thing", 10
-            )
+            result = await extract_and_create_followups("1. Do the thing\n2. Do another thing", 10)

        assert result["success"] is True
        assert 200 in result["created"]