From 160fd50a28c8324d54a12f422ac06221cc8b1cb0 Mon Sep 17 00:00:00 2001
From: yetuge <182123929+yetuge@users.noreply.github.com>
Date: Mon, 28 Sep 2026 22:36:19 +0800
Subject: [PATCH] fix(sandbox): reject non-finite health_check_skip_seconds in
 config (#5997)

`health_check_skip_seconds` was the only float field in SandboxConfig
without `allow_inf_nan=False`, and `ge=0` alone does not stop inf
(`inf >= 0` is true). A config.yaml value of `1e999` loads as the string
"1e999" and pydantic's float coercion turns it into inf, so the field
accepted it and the BoxLite warm-reuse site then skipped the health
check permanently: `skip_seconds > 0 and (time.time() - released_at) <
skip_seconds` holds forever for inf, so every box this instance
recently released is promoted without validation instead of failing
fast at config load.

Add `allow_inf_nan=False`, matching the sibling sandbox float fields
(`bash_command_timeout`, `renewal_interval_seconds`, `ttl_multiplier`)
and the ownership lease-TTL model validator.

Red/green: `test_sandbox_config_rejects_non_finite_health_check_skip_seconds`
parametrizes inf and "1e999"; both were accepted before the fix (RED)
and are rejected after. Full boxlite suite: 54 passed / 15 skipped.

Regression: the sandbox/config/ownership subset fails 17 tests on this
Windows host both with and without the change, with a byte-identical
failure-name set (environment-type: process-spawn and file-stat
behavior), so no regressions are introduced.

Signed-off-by: yetuge <2219677952@qq.com>
---
 .../harness/deerflow/config/sandbox_config.py |  1 +
 backend/tests/test_boxlite_provider.py        | 21 +++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/backend/packages/harness/deerflow/config/sandbox_config.py b/backend/packages/harness/deerflow/config/sandbox_config.py
index 4ce45a4ace..cc42e380a1 100644
--- a/backend/packages/harness/deerflow/config/sandbox_config.py
+++ b/backend/packages/harness/deerflow/config/sandbox_config.py
@@ -236,6 +236,7 @@ class SandboxConfig(BaseModel):
     health_check_skip_seconds: float | None = Field(
         default=None,
         ge=0,
+        allow_inf_nan=False,
         description="BoxLite-only reclaim skip window in seconds for boxes recently released by this provider instance. Set to 0 to always validate before warm reuse.",
     )
     ownership: SandboxOwnershipConfig | None = Field(
diff --git a/backend/tests/test_boxlite_provider.py b/backend/tests/test_boxlite_provider.py
index 736d6d45e6..138fbf56ef 100644
--- a/backend/tests/test_boxlite_provider.py
+++ b/backend/tests/test_boxlite_provider.py
@@ -18,9 +18,11 @@ import time
 import types
 
 import pytest
+from pydantic import ValidationError
 
 from deerflow.community.boxlite.box import BoxliteBox
 from deerflow.community.boxlite.provider import BoxliteProvider, _import_simplebox
+from deerflow.config.sandbox_config import SandboxConfig
 from deerflow.trace_context import get_current_trace_id, request_trace_context
 
 _LEGACY_COLLIDING_IDENTITIES = (
@@ -543,6 +545,25 @@ async def test_acquire_async_propagates_request_trace_context(monkeypatch):
         await asyncio.to_thread(provider.shutdown)
 
 
+@pytest.mark.parametrize("value", [float("inf"), "1e999"])
+def test_sandbox_config_rejects_non_finite_health_check_skip_seconds(value):
+    """`ge=0` alone lets a non-finite skip window through.
+
+    `health_check_skip_seconds: 1e999` in config.yaml loads as the string
+    "1e999" and pydantic's float coercion turns it into inf; `ge=0` accepts
+    inf (inf >= 0). At the warm-reuse site the check `skip_seconds > 0 and
+    (now - released_at) < skip_seconds` then holds forever, so recently
+    released boxes are promoted without the health check permanently instead
+    of failing fast at config load. `allow_inf_nan=False` (as already set on
+    the sibling sandbox float fields) makes the config layer reject it.
+    """
+    with pytest.raises(ValidationError):
+        SandboxConfig(
+            use="deerflow.community.boxlite.provider:BoxliteProvider",
+            health_check_skip_seconds=value,
+        )
+
+
 def test_explicit_recent_reclaim_skip_avoids_health_check(monkeypatch):
     """A configured skip window can reclaim recently released boxes without a ping."""
     monkeypatch.setattr(