test(anthropic): add regression tests for thinking modes incl. adaptive

Also update schema comment to mention 'adaptive' as a valid value.

Made-with: Cursor

nanobot/config/schema.py

@@ -74,7 +74,7 @@ class AgentDefaults(Base):
     max_tool_iterations: int = 200
     max_tool_result_chars: int = 16_000
     provider_retry_mode: Literal["standard", "persistent"] = "standard"
-    reasoning_effort: str | None = None  # low / medium / high - enables LLM thinking mode
+    reasoning_effort: str | None = None  # low / medium / high / adaptive - enables LLM thinking mode
     timezone: str = "UTC"  # IANA timezone, e.g. "Asia/Shanghai", "America/New_York"
     dream: DreamConfig = Field(default_factory=DreamConfig)
 

tests/providers/test_anthropic_thinking.py

@@ -0,0 +1,65 @@
+"""Tests for Anthropic provider thinking / reasoning_effort modes."""
+
+from __future__ import annotations
+
+from unittest.mock import patch
+
+from nanobot.providers.anthropic_provider import AnthropicProvider
+
+
+def _make_provider(model: str = "claude-sonnet-4-6") -> AnthropicProvider:
+    with patch("anthropic.AsyncAnthropic"):
+        return AnthropicProvider(api_key="sk-test", default_model=model)
+
+
+def _build(provider: AnthropicProvider, reasoning_effort: str | None, **overrides):
+    defaults = dict(
+        messages=[{"role": "user", "content": "hello"}],
+        tools=None,
+        model=None,
+        max_tokens=4096,
+        temperature=0.7,
+        reasoning_effort=reasoning_effort,
+        tool_choice=None,
+        supports_caching=False,
+    )
+    defaults.update(overrides)
+    return provider._build_kwargs(**defaults)
+
+
+def test_adaptive_sets_type_adaptive() -> None:
+    kw = _build(_make_provider(), "adaptive")
+    assert kw["thinking"] == {"type": "adaptive"}
+
+
+def test_adaptive_forces_temperature_one() -> None:
+    kw = _build(_make_provider(), "adaptive")
+    assert kw["temperature"] == 1.0
+
+
+def test_adaptive_does_not_inflate_max_tokens() -> None:
+    kw = _build(_make_provider(), "adaptive", max_tokens=2048)
+    assert kw["max_tokens"] == 2048
+
+
+def test_adaptive_no_budget_tokens() -> None:
+    kw = _build(_make_provider(), "adaptive")
+    assert "budget_tokens" not in kw["thinking"]
+
+
+def test_high_uses_enabled_with_budget() -> None:
+    kw = _build(_make_provider(), "high", max_tokens=4096)
+    assert kw["thinking"]["type"] == "enabled"
+    assert kw["thinking"]["budget_tokens"] == max(8192, 4096)
+    assert kw["max_tokens"] >= kw["thinking"]["budget_tokens"] + 4096
+
+
+def test_low_uses_small_budget() -> None:
+    kw = _build(_make_provider(), "low")
+    assert kw["thinking"] == {"type": "enabled", "budget_tokens": 1024}
+
+
+def test_none_does_not_enable_thinking() -> None:
+    kw = _build(_make_provider(), None)
+    assert "thinking" not in kw
+    assert kw["temperature"] == 0.7