From d7a09d975b6324922e93b50074e0fe20f4bd4944 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 24 May 2026 16:14:12 +0000
Subject: [PATCH] Drop seed and parallel_tool_calls for Kimi too (PR #5711)

Kimi K2.5/K2.6 chat schema documents temperature, top_p and a small
fixed set of knobs; seed and parallel_tool_calls are not in it. The
frontend already hides those controls (provider-capabilities.ts), so
the only way they reach Kimi is a stale client or a direct API caller.
Add them to body_omit so the registry strips them on the wire instead
of relying on the upstream to 400.

Sync the Kimi web-search bypass test to assert both fields are dropped
alongside frequency_penalty/temperature/top_p.
---
 studio/backend/core/inference/providers.py     | 18 +++++++++++++-----
 .../tests/test_sampling_params_routing.py      |  8 ++++----
 2 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/studio/backend/core/inference/providers.py b/studio/backend/core/inference/providers.py
index b967123ada..0f5620add7 100644
--- a/studio/backend/core/inference/providers.py
+++ b/studio/backend/core/inference/providers.py
@@ -158,11 +158,19 @@ PROVIDER_REGISTRY: dict[str, dict[str, Any]] = {
         "notes": "Moonshot API key. China: use base URL https://api.moonshot.cn/v1",
         "model_id_allowlist": re.compile(r"^kimi-k2\.[56]$"),
         # Both k2.6 and k2.5 are reasoning-class. The API rejects
-        # custom sampling: "invalid temperature: only 1 is allowed for
-        # this model" (and the same shape for top_p). frequency_penalty
-        # is reported by reviewers to follow the same lock; strip it
-        # too so non-default values from stale clients do not 400.
-        "body_omit": ("temperature", "top_p", "frequency_penalty"),
+        # custom sampling ("invalid temperature: only 1 is allowed for
+        # this model", same for top_p). frequency_penalty follows the
+        # same lock on those models. seed and parallel_tool_calls are
+        # not in Kimi's documented chat schema; strip them too so a
+        # stale client or direct API caller cannot smuggle them onto
+        # the wire and 400 the request.
+        "body_omit": (
+            "temperature",
+            "top_p",
+            "frequency_penalty",
+            "seed",
+            "parallel_tool_calls",
+        ),
         # Kimi accepts at most 5 stop strings (each <= 32 bytes) per
         # https://platform.kimi.ai/docs/api/chat
         "stop_max": 5,
diff --git a/studio/backend/tests/test_sampling_params_routing.py b/studio/backend/tests/test_sampling_params_routing.py
index 90509ead5d..889fe2621e 100644
--- a/studio/backend/tests/test_sampling_params_routing.py
+++ b/studio/backend/tests/test_sampling_params_routing.py
@@ -573,14 +573,14 @@ def test_kimi_web_search_bypass_forwards_new_sampling_fields(monkeypatch):
 
     _drive(run())
     body = captured["body"]
-    # Per-provider drops: Kimi locks frequency_penalty/temperature/top_p.
+    # Kimi locks these: stripped by body_omit in providers.py.
     assert "frequency_penalty" not in body, body
     assert "temperature" not in body, body
     assert "top_p" not in body, body
-    # Other knobs forward through the bypass.
-    assert body.get("seed") == 7, body
+    assert "seed" not in body, body
+    assert "parallel_tool_calls" not in body, body
+    # Knobs not on Kimi's drop-list forward through the bypass.
     assert body.get("stop") == ["END"], body
-    assert body.get("parallel_tool_calls") is False, body
     assert body.get("presence_penalty") == 0.5, body