Merge remote-tracking branch 'origin/main' into fix/structured-retry-classification-main

# Conflicts:
#	nanobot/providers/anthropic_provider.py
#	nanobot/providers/base.py
#	nanobot/providers/openai_compat_provider.py

tests/providers/test_provider_retry.py

@@ -240,6 +240,39 @@ async def test_chat_with_retry_uses_retry_after_and_emits_wait_progress(monkeypa
     assert progress and "7s" in progress[0]
 
 
+def test_extract_retry_after_supports_common_provider_formats() -> None:
+    assert LLMProvider._extract_retry_after('{"error":{"retry_after":20}}') == 20.0
+    assert LLMProvider._extract_retry_after("Rate limit reached, please try again in 20s") == 20.0
+    assert LLMProvider._extract_retry_after("retry-after: 20") == 20.0
+
+
+def test_extract_retry_after_from_headers_supports_numeric_and_http_date() -> None:
+    assert LLMProvider._extract_retry_after_from_headers({"Retry-After": "20"}) == 20.0
+    assert LLMProvider._extract_retry_after_from_headers({"retry-after": "20"}) == 20.0
+    assert LLMProvider._extract_retry_after_from_headers(
+        {"Retry-After": "Wed, 21 Oct 2015 07:28:00 GMT"},
+    ) == 0.1
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_prefers_structured_retry_after_when_present(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        LLMResponse(content="429 rate limit", finish_reason="error", retry_after=9.0),
+        LLMResponse(content="ok"),
+    ])
+    delays: list[float] = []
+
+    async def _fake_sleep(delay: float) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+    assert response.content == "ok"
+    assert delays == [9.0]
+
+
 @pytest.mark.asyncio
 async def test_chat_with_retry_retries_structured_status_code_without_keyword(monkeypatch) -> None:
     provider = ScriptedProvider([

tests/providers/test_provider_retry_after_hints.py

@@ -0,0 +1,42 @@
+from types import SimpleNamespace
+
+from nanobot.providers.anthropic_provider import AnthropicProvider
+from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+def test_openai_compat_error_captures_retry_after_from_headers() -> None:
+    err = Exception("boom")
+    err.doc = None
+    err.response = SimpleNamespace(
+        text='{"error":{"message":"Rate limit exceeded"}}',
+        headers={"Retry-After": "20"},
+    )
+
+    response = OpenAICompatProvider._handle_error(err)
+
+    assert response.retry_after == 20.0
+
+
+def test_azure_openai_error_captures_retry_after_from_headers() -> None:
+    err = Exception("boom")
+    err.body = {"message": "Rate limit exceeded"}
+    err.response = SimpleNamespace(
+        text='{"error":{"message":"Rate limit exceeded"}}',
+        headers={"Retry-After": "20"},
+    )
+
+    response = AzureOpenAIProvider._handle_error(err)
+
+    assert response.retry_after == 20.0
+
+
+def test_anthropic_error_captures_retry_after_from_headers() -> None:
+    err = Exception("boom")
+    err.response = SimpleNamespace(
+        headers={"Retry-After": "20"},
+    )
+
+    response = AnthropicProvider._handle_error(err)
+
+    assert response.retry_after == 20.0

tests/providers/test_provider_sdk_retry_defaults.py

@@ -0,0 +1,33 @@
+from unittest.mock import patch
+
+from nanobot.providers.anthropic_provider import AnthropicProvider
+from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+def test_openai_compat_disables_sdk_retries_by_default() -> None:
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI") as mock_client:
+        OpenAICompatProvider(api_key="sk-test", default_model="gpt-4o")
+
+    kwargs = mock_client.call_args.kwargs
+    assert kwargs["max_retries"] == 0
+
+
+def test_anthropic_disables_sdk_retries_by_default() -> None:
+    with patch("anthropic.AsyncAnthropic") as mock_client:
+        AnthropicProvider(api_key="sk-test", default_model="claude-sonnet-4-5")
+
+    kwargs = mock_client.call_args.kwargs
+    assert kwargs["max_retries"] == 0
+
+
+def test_azure_openai_disables_sdk_retries_by_default() -> None:
+    with patch("nanobot.providers.azure_openai_provider.AsyncOpenAI") as mock_client:
+        AzureOpenAIProvider(
+            api_key="sk-test",
+            api_base="https://example.openai.azure.com",
+            default_model="gpt-4.1",
+        )
+
+    kwargs = mock_client.call_args.kwargs
+    assert kwargs["max_retries"] == 0

tests/providers/test_reasoning_content.py

@@ -0,0 +1,128 @@
+"""Tests for reasoning_content extraction in OpenAICompatProvider.
+
+Covers non-streaming (_parse) and streaming (_parse_chunks) paths for
+providers that return a reasoning_content field (e.g. MiMo, DeepSeek-R1).
+"""
+
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+# ── _parse: non-streaming ─────────────────────────────────────────────────
+
+
+def test_parse_dict_extracts_reasoning_content() -> None:
+    """reasoning_content at message level is surfaced in LLMResponse."""
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    response = {
+        "choices": [{
+            "message": {
+                "content": "42",
+                "reasoning_content": "Let me think step by step…",
+            },
+            "finish_reason": "stop",
+        }],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 10, "total_tokens": 15},
+    }
+
+    result = provider._parse(response)
+
+    assert result.content == "42"
+    assert result.reasoning_content == "Let me think step by step…"
+
+
+def test_parse_dict_reasoning_content_none_when_absent() -> None:
+    """reasoning_content is None when the response doesn't include it."""
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    response = {
+        "choices": [{
+            "message": {"content": "hello"},
+            "finish_reason": "stop",
+        }],
+    }
+
+    result = provider._parse(response)
+
+    assert result.reasoning_content is None
+
+
+# ── _parse_chunks: streaming dict branch ─────────────────────────────────
+
+
+def test_parse_chunks_dict_accumulates_reasoning_content() -> None:
+    """reasoning_content deltas in dict chunks are joined into one string."""
+    chunks = [
+        {
+            "choices": [{
+                "finish_reason": None,
+                "delta": {"content": None, "reasoning_content": "Step 1. "},
+            }],
+        },
+        {
+            "choices": [{
+                "finish_reason": None,
+                "delta": {"content": None, "reasoning_content": "Step 2."},
+            }],
+        },
+        {
+            "choices": [{
+                "finish_reason": "stop",
+                "delta": {"content": "answer"},
+            }],
+        },
+    ]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.content == "answer"
+    assert result.reasoning_content == "Step 1. Step 2."
+
+
+def test_parse_chunks_dict_reasoning_content_none_when_absent() -> None:
+    """reasoning_content is None when no chunk contains it."""
+    chunks = [
+        {"choices": [{"finish_reason": "stop", "delta": {"content": "hi"}}]},
+    ]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.content == "hi"
+    assert result.reasoning_content is None
+
+
+# ── _parse_chunks: streaming SDK-object branch ────────────────────────────
+
+
+def _make_reasoning_chunk(reasoning: str | None, content: str | None, finish: str | None):
+    delta = SimpleNamespace(content=content, reasoning_content=reasoning, tool_calls=None)
+    choice = SimpleNamespace(finish_reason=finish, delta=delta)
+    return SimpleNamespace(choices=[choice], usage=None)
+
+
+def test_parse_chunks_sdk_accumulates_reasoning_content() -> None:
+    """reasoning_content on SDK delta objects is joined across chunks."""
+    chunks = [
+        _make_reasoning_chunk("Think… ", None, None),
+        _make_reasoning_chunk("Done.", None, None),
+        _make_reasoning_chunk(None, "result", "stop"),
+    ]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.content == "result"
+    assert result.reasoning_content == "Think… Done."
+
+
+def test_parse_chunks_sdk_reasoning_content_none_when_absent() -> None:
+    """reasoning_content is None when SDK deltas carry no reasoning_content."""
+    chunks = [_make_reasoning_chunk(None, "hello", "stop")]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.reasoning_content is None