mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-03 17:27:37 +08:00
76edc40ab0
Builds on #16855 (@lsdsjy) which fixed DeepSeek v4 reasoning_content replay via model_extra fallback + capturing tool_calls at method entry. Kimi / Moonshot thinking mode enforces the same echo-back contract and hits the same 400 when a tool-call turn is persisted without reasoning_content. - _build_assistant_message: pad branch now uses _needs_thinking_reasoning_pad() (DeepSeek OR Kimi) instead of _needs_deepseek_tool_reasoning() alone. - Extract _needs_thinking_reasoning_pad() and reuse it in _copy_reasoning_content_for_api so both sites share one predicate. - tests/run_agent/test_deepseek_reasoning_content_echo.py: add TestBuildAssistantMessagePadsStrictProviders parametrized over DeepSeek (attr=None, attr-absent), Kimi (attr=None), Moonshot (via base_url), and an OpenRouter negative control that must NOT pad. Proven to fail 2/5 cases on Kimi/Moonshot without this change. - scripts/release.py: add AUTHOR_MAP entries for lsdsjy and season179. Refs #17400. Co-authored-by: season179 <season.saw@gmail.com>
442 lines
17 KiB
Python
442 lines
17 KiB
Python
"""Regression test: DeepSeek V4 thinking mode reasoning_content echo.
|
|
|
|
DeepSeek V4-flash / V4-pro thinking mode requires ``reasoning_content`` on
|
|
every assistant message that carries ``tool_calls``. When a persisted
|
|
session replays an assistant tool-call turn that was recorded without the
|
|
field, DeepSeek rejects the next request with HTTP 400::
|
|
|
|
The reasoning_content in the thinking mode must be passed back to the API.
|
|
|
|
Fix covers three paths:
|
|
|
|
1. ``_build_assistant_message`` — new tool-call messages without raw
|
|
reasoning_content get ``""`` pinned at creation time so nothing gets
|
|
persisted poisoned.
|
|
2. ``_copy_reasoning_content_for_api`` — already-poisoned history replays
|
|
with ``reasoning_content=""`` injected defensively.
|
|
3. Detection covers three signals: ``provider == "deepseek"``,
|
|
``"deepseek" in model``, and ``api.deepseek.com`` host match. The third
|
|
catches custom-provider setups pointing at DeepSeek.
|
|
|
|
Refs #15250 / #15353.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from run_agent import AIAgent
|
|
|
|
|
|
def _make_agent(provider: str = "", model: str = "", base_url: str = "") -> AIAgent:
|
|
agent = object.__new__(AIAgent)
|
|
agent.provider = provider
|
|
agent.model = model
|
|
agent.base_url = base_url
|
|
agent.verbose_logging = False
|
|
agent.reasoning_callback = None
|
|
agent.stream_delta_callback = None
|
|
agent._stream_callback = None
|
|
return agent
|
|
|
|
|
|
_ATTR_ABSENT = object()
|
|
_EXPECT_NOT_PRESENT = object()
|
|
|
|
|
|
def _sdk_tool_call(call_id: str = "c1", name: str = "terminal", arguments: str = "{}"):
|
|
"""Minimal SDK-shaped tool_call object that satisfies the builder's iteration."""
|
|
return SimpleNamespace(
|
|
id=call_id,
|
|
call_id=call_id,
|
|
type="function",
|
|
function=SimpleNamespace(name=name, arguments=arguments),
|
|
extra_content=None,
|
|
)
|
|
|
|
|
|
def _build_sdk_message(reasoning_content=_ATTR_ABSENT, **extra):
|
|
"""SDK-shaped assistant message; ``reasoning_content`` defaults to absent."""
|
|
kwargs = {"content": "", **extra}
|
|
if reasoning_content is not _ATTR_ABSENT:
|
|
kwargs["reasoning_content"] = reasoning_content
|
|
return SimpleNamespace(**kwargs)
|
|
|
|
|
|
class TestNeedsDeepSeekToolReasoning:
|
|
"""_needs_deepseek_tool_reasoning() recognises all three detection signals."""
|
|
|
|
def test_provider_deepseek(self) -> None:
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
assert agent._needs_deepseek_tool_reasoning() is True
|
|
|
|
def test_model_substring(self) -> None:
|
|
# Custom provider pointing at DeepSeek with provider='custom'
|
|
agent = _make_agent(provider="custom", model="deepseek-v4-pro")
|
|
assert agent._needs_deepseek_tool_reasoning() is True
|
|
|
|
def test_base_url_host(self) -> None:
|
|
agent = _make_agent(
|
|
provider="custom",
|
|
model="some-aliased-name",
|
|
base_url="https://api.deepseek.com/v1",
|
|
)
|
|
assert agent._needs_deepseek_tool_reasoning() is True
|
|
|
|
def test_provider_case_insensitive(self) -> None:
|
|
agent = _make_agent(provider="DeepSeek", model="")
|
|
assert agent._needs_deepseek_tool_reasoning() is True
|
|
|
|
def test_non_deepseek_provider(self) -> None:
|
|
agent = _make_agent(
|
|
provider="openrouter",
|
|
model="anthropic/claude-sonnet-4.6",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
)
|
|
assert agent._needs_deepseek_tool_reasoning() is False
|
|
|
|
def test_empty_everything(self) -> None:
|
|
agent = _make_agent()
|
|
assert agent._needs_deepseek_tool_reasoning() is False
|
|
|
|
|
|
class TestCopyReasoningContentForApi:
|
|
"""_copy_reasoning_content_for_api pads reasoning_content for DeepSeek tool-calls."""
|
|
|
|
def test_deepseek_tool_call_poisoned_history_gets_empty_string(self) -> None:
|
|
"""Already-poisoned history (no reasoning_content, no reasoning) gets ''."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg.get("reasoning_content") == ""
|
|
|
|
def test_deepseek_assistant_no_tool_call_gets_padded(self) -> None:
|
|
"""DeepSeek thinking mode pads ALL assistant turns, even without tool_calls."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
source = {"role": "assistant", "content": "hello"}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg.get("reasoning_content") == ""
|
|
|
|
def test_deepseek_explicit_reasoning_content_preserved(self) -> None:
|
|
"""When reasoning_content is already set, it's copied verbatim."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
source = {
|
|
"role": "assistant",
|
|
"reasoning_content": "<think>real chain of thought</think>",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg["reasoning_content"] == "<think>real chain of thought</think>"
|
|
|
|
def test_deepseek_reasoning_field_promoted(self) -> None:
|
|
"""When only 'reasoning' is set, it gets promoted to reasoning_content."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "thought trace",
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg["reasoning_content"] == "thought trace"
|
|
|
|
def test_deepseek_poisoned_cross_provider_history_padded(self) -> None:
|
|
"""Cross-provider tool-call turn (#15748): MiniMax reasoning leaks
|
|
to DeepSeek/Kimi request.
|
|
|
|
If the source turn has tool_calls AND a 'reasoning' field but NO
|
|
'reasoning_content' key, it's from a prior provider (the DeepSeek
|
|
build path pins reasoning_content at creation). Inject "" instead
|
|
of forwarding the prior provider's chain of thought.
|
|
"""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "MiniMax chain of thought from a prior turn",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg["reasoning_content"] == ""
|
|
|
|
def test_kimi_poisoned_cross_provider_history_padded(self) -> None:
|
|
"""Kimi path of #15748 — same rule as DeepSeek."""
|
|
agent = _make_agent(provider="kimi-coding", model="kimi-k2.5")
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "DeepSeek chain of thought from a prior turn",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg["reasoning_content"] == ""
|
|
|
|
def test_kimi_path_still_works(self) -> None:
|
|
"""Existing Kimi detection still pads reasoning_content."""
|
|
agent = _make_agent(provider="kimi-coding", model="kimi-k2.5")
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg.get("reasoning_content") == ""
|
|
|
|
def test_kimi_moonshot_base_url(self) -> None:
|
|
agent = _make_agent(
|
|
provider="custom", model="kimi-k2", base_url="https://api.moonshot.ai/v1"
|
|
)
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg.get("reasoning_content") == ""
|
|
|
|
def test_non_thinking_provider_not_padded(self) -> None:
|
|
"""Providers that don't require the echo are untouched."""
|
|
agent = _make_agent(
|
|
provider="openrouter",
|
|
model="anthropic/claude-sonnet-4.6",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
)
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert "reasoning_content" not in api_msg
|
|
|
|
def test_deepseek_custom_base_url(self) -> None:
|
|
"""Custom provider pointing at api.deepseek.com is detected via host."""
|
|
agent = _make_agent(
|
|
provider="custom",
|
|
model="whatever",
|
|
base_url="https://api.deepseek.com/v1",
|
|
)
|
|
source = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [{"id": "c1", "function": {"name": "terminal"}}],
|
|
}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert api_msg.get("reasoning_content") == ""
|
|
|
|
def test_non_assistant_role_ignored(self) -> None:
|
|
"""User/tool messages are left alone."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
source = {"role": "user", "content": "hi"}
|
|
api_msg: dict = {}
|
|
agent._copy_reasoning_content_for_api(source, api_msg)
|
|
assert "reasoning_content" not in api_msg
|
|
|
|
|
|
class TestBuildAssistantMessageDeepSeekReasoningContent:
|
|
"""_build_assistant_message pins replay-safe DeepSeek tool-call state."""
|
|
|
|
def test_deepseek_tool_call_reasoning_is_backfilled_into_reasoning_content(self) -> None:
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
assistant_message = SimpleNamespace(
|
|
content=None,
|
|
reasoning="DeepSeek tool-call reasoning",
|
|
reasoning_content=None,
|
|
reasoning_details=None,
|
|
codex_reasoning_items=None,
|
|
codex_message_items=None,
|
|
tool_calls=[
|
|
SimpleNamespace(
|
|
id="call_1",
|
|
call_id=None,
|
|
response_item_id=None,
|
|
type="function",
|
|
function=SimpleNamespace(name="terminal", arguments="{}"),
|
|
)
|
|
],
|
|
)
|
|
|
|
msg = agent._build_assistant_message(assistant_message, "tool_calls")
|
|
|
|
assert msg["reasoning_content"] == "DeepSeek tool-call reasoning"
|
|
assert msg["tool_calls"][0]["id"] == "call_1"
|
|
|
|
def test_deepseek_model_extra_reasoning_content_is_preserved(self) -> None:
|
|
"""OpenAI SDK stores unknown provider fields in model_extra."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
assistant_message = SimpleNamespace(
|
|
content=None,
|
|
reasoning=None,
|
|
reasoning_content=None,
|
|
model_extra={"reasoning_content": "DeepSeek model_extra reasoning"},
|
|
reasoning_details=None,
|
|
codex_reasoning_items=None,
|
|
codex_message_items=None,
|
|
tool_calls=[
|
|
SimpleNamespace(
|
|
id="call_1",
|
|
call_id=None,
|
|
response_item_id=None,
|
|
type="function",
|
|
function=SimpleNamespace(name="terminal", arguments="{}"),
|
|
)
|
|
],
|
|
)
|
|
|
|
msg = agent._build_assistant_message(assistant_message, "tool_calls")
|
|
|
|
assert msg["reasoning_content"] == "DeepSeek model_extra reasoning"
|
|
|
|
def test_deepseek_tool_call_without_raw_reasoning_content_gets_empty_string(self) -> None:
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-flash")
|
|
assistant_message = SimpleNamespace(
|
|
content=None,
|
|
reasoning=None,
|
|
reasoning_content=None,
|
|
reasoning_details=None,
|
|
codex_reasoning_items=None,
|
|
codex_message_items=None,
|
|
tool_calls=[
|
|
SimpleNamespace(
|
|
id="call_1",
|
|
call_id=None,
|
|
response_item_id=None,
|
|
type="function",
|
|
function=SimpleNamespace(name="terminal", arguments="{}"),
|
|
)
|
|
],
|
|
)
|
|
|
|
msg = agent._build_assistant_message(assistant_message, "tool_calls")
|
|
|
|
assert msg["reasoning_content"] == ""
|
|
assert msg["tool_calls"][0]["id"] == "call_1"
|
|
|
|
|
|
class TestBuildAssistantMessagePadsStrictProviders:
|
|
"""Regression for #17400: _build_assistant_message must pin reasoning_content
|
|
on tool-call turns when the active provider enforces echo-back, regardless
|
|
of whether the SDK exposed reasoning_content as None, omitted it entirely,
|
|
or returned an empty thinking block.
|
|
|
|
Prior to the fix, the pad branch was guarded by ``msg.get("tool_calls")``,
|
|
which was always falsy because tool_calls were assigned later in the same
|
|
method. Persisted history accumulated assistant tool-call turns with no
|
|
reasoning_content; the next replay 400'd on DeepSeek/Kimi.
|
|
"""
|
|
|
|
@pytest.mark.parametrize(
|
|
"provider,model,base_url,sdk_reasoning_content,expected",
|
|
[
|
|
pytest.param(
|
|
"deepseek", "deepseek-v4-pro", "",
|
|
None, "",
|
|
id="deepseek-attr-none",
|
|
),
|
|
pytest.param(
|
|
"deepseek", "deepseek-v4-pro", "",
|
|
_ATTR_ABSENT, "",
|
|
id="deepseek-attr-absent",
|
|
),
|
|
pytest.param(
|
|
"kimi-coding", "kimi-k2.6", "",
|
|
None, "",
|
|
id="kimi-attr-none",
|
|
),
|
|
pytest.param(
|
|
"custom", "kimi-k2", "https://api.moonshot.ai/v1",
|
|
_ATTR_ABSENT, "",
|
|
id="moonshot-base-url",
|
|
),
|
|
pytest.param(
|
|
"openrouter", "anthropic/claude-sonnet-4.6", "https://openrouter.ai/api/v1",
|
|
_ATTR_ABSENT, _EXPECT_NOT_PRESENT,
|
|
id="openrouter-no-pad",
|
|
),
|
|
],
|
|
)
|
|
def test_tool_call_reasoning_content_pad(
|
|
self, provider, model, base_url, sdk_reasoning_content, expected,
|
|
) -> None:
|
|
agent = _make_agent(provider=provider, model=model, base_url=base_url)
|
|
msg_in = _build_sdk_message(
|
|
reasoning_content=sdk_reasoning_content,
|
|
tool_calls=[_sdk_tool_call()],
|
|
)
|
|
msg = agent._build_assistant_message(msg_in, finish_reason="tool_calls")
|
|
if expected is _EXPECT_NOT_PRESENT:
|
|
assert "reasoning_content" not in msg
|
|
else:
|
|
assert msg["reasoning_content"] == expected
|
|
|
|
def test_tool_call_preserves_real_reasoning_content(self) -> None:
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-pro")
|
|
msg_in = _build_sdk_message(
|
|
reasoning_content="actual chain of thought",
|
|
tool_calls=[_sdk_tool_call()],
|
|
)
|
|
msg = agent._build_assistant_message(msg_in, finish_reason="tool_calls")
|
|
assert msg["reasoning_content"] == "actual chain of thought"
|
|
|
|
def test_text_only_turn_not_padded_by_tool_call_branch(self) -> None:
|
|
"""Plain-text turns rely on _copy_reasoning_content_for_api at replay
|
|
time, not on this builder's tool-call pad."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-pro")
|
|
msg_in = SimpleNamespace(content="hello", tool_calls=None)
|
|
msg = agent._build_assistant_message(msg_in, finish_reason="stop")
|
|
assert "tool_calls" not in msg
|
|
assert "reasoning_content" not in msg
|
|
|
|
def test_streamed_reasoning_text_promoted_over_pad(self) -> None:
|
|
"""When ``.reasoning`` carries streamed thinking, it must be promoted
|
|
to reasoning_content rather than overwritten with the empty pad."""
|
|
agent = _make_agent(provider="deepseek", model="deepseek-v4-pro")
|
|
msg_in = _build_sdk_message(
|
|
reasoning="streamed thoughts",
|
|
tool_calls=[_sdk_tool_call()],
|
|
)
|
|
msg = agent._build_assistant_message(msg_in, finish_reason="tool_calls")
|
|
assert msg["reasoning_content"] == "streamed thoughts"
|
|
|
|
|
|
class TestNeedsKimiToolReasoning:
|
|
"""The extracted _needs_kimi_tool_reasoning() helper keeps Kimi behavior intact."""
|
|
|
|
@pytest.mark.parametrize(
|
|
"provider,base_url",
|
|
[
|
|
("kimi-coding", ""),
|
|
("kimi-coding-cn", ""),
|
|
("custom", "https://api.kimi.com/v1"),
|
|
("custom", "https://api.moonshot.ai/v1"),
|
|
("custom", "https://api.moonshot.cn/v1"),
|
|
],
|
|
)
|
|
def test_kimi_signals(self, provider: str, base_url: str) -> None:
|
|
agent = _make_agent(provider=provider, model="kimi-k2", base_url=base_url)
|
|
assert agent._needs_kimi_tool_reasoning() is True
|
|
|
|
def test_non_kimi_provider(self) -> None:
|
|
agent = _make_agent(
|
|
provider="openrouter",
|
|
model="moonshotai/kimi-k2",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
)
|
|
# model name contains 'moonshot' but host is openrouter — should be False
|
|
assert agent._needs_kimi_tool_reasoning() is False
|