core/agent: run a hosted search as the surface's own tool

DeepSeek's Anthropic compat runs a hosted ``web_search`` itself and answers with
the blocks that search produced — ``thinking``, ``server_tool_use`` (the query)
and ``web_search_tool_result`` — so the content union that knew only text and
tool_use could not decode a live search turn. It carries them now, ``tools``
accepts the opaque server-tool dicts the surface declares, and
``web_search_tool_result.content`` stays loose on purpose: its
``web_search_result`` entries hold an ``encrypted_content`` the API demands back
unchanged (a trimmed result is answered with 422 "missing field
``encrypted_content``").

``provider_tools`` reached only the Responses surface, and the Anthropic one
wants its own definition of the same intent: a bare ``web_search`` becomes
``{type="web_search_20250305", name="web_search"}`` (the server tool Claude
declares and DeepSeek's compat reads, keeping a ``max_uses`` cap or any other
key), merged after the local function tools.

Such a tool is the server's: it streams ``input_json_delta`` fragments like a
call, and reading them as one asked the registry for a tool the server had
already run. Block types are now tracked, so only a ``tool_use`` block becomes a
tool call; the search blocks and ``thinking`` are skipped by the response
mapping (the answer the model wrote already used them) and never executed.
This commit is contained in:
2026-10-06 23:35:23 +08:00
parent 88b93a8dfe
commit 1fa41c9fde
7 changed files with 376 additions and 18 deletions
+68
View File
@@ -13,6 +13,7 @@ from plyngent.agent.messages_bridge import (
anthropic_usage_to_dict,
chat_messages_to_anthropic,
chat_param_to_anthropic_param,
provider_tools_to_anthropic_tools,
tool_items_to_anthropic_tools,
)
from plyngent.lmproto.anthropic.model import (
@@ -20,10 +21,14 @@ from plyngent.lmproto.anthropic.model import (
AnthropicMessageResponse,
AnthropicResponseText,
AnthropicResponseToolUse,
AnthropicServerToolUseContent,
AnthropicThinkingContent,
AnthropicToolDefinition,
AnthropicToolResultContent,
AnthropicToolUseContent,
AnthropicUsage,
AnthropicUserMessage,
AnthropicWebSearchToolResultContent,
)
from plyngent.lmproto.openai_compatible.model import (
AssistantChatMessage,
@@ -151,6 +156,69 @@ def test_anthropic_response_to_assistant_with_tools() -> None:
assert '"a":1' in call.function.arguments or '"a": 1' in call.function.arguments
def test_anthropic_response_to_assistant_ignores_server_tool_blocks() -> None:
"""A server-side search is not a call for the registry, nor part of the message."""
response = AnthropicMessageResponse(
id="msg_search",
model="deepseek-flash",
stop_reason="end_turn",
content=[
AnthropicThinkingContent(thinking="Let me search.", signature="sig-1"),
AnthropicServerToolUseContent(id="call_00_1", name="web_search", input={"query": "DeepSeek-V4"}),
AnthropicWebSearchToolResultContent(
tool_use_id="call_00_1",
content=[{"type": "web_search_result", "url": "https://api-docs.deepseek.com"}],
),
AnthropicResponseText(text="DeepSeek-V4 is out."),
],
usage=AnthropicUsage(input_tokens=16592, output_tokens=1419),
)
assistant = anthropic_response_to_assistant(response)
assert assistant.content == "DeepSeek-V4 is out."
assert assistant.tool_calls is UNSET
def test_provider_tools_to_anthropic_tools_maps_the_search_intent() -> None:
"""The config default (``{"type": "web_search"}``) becomes the server tool."""
assert provider_tools_to_anthropic_tools(None) == []
assert provider_tools_to_anthropic_tools([]) == []
assert provider_tools_to_anthropic_tools([{"type": "web_search"}]) == [
{"type": "web_search_20250305", "name": "web_search"}
]
# A cap (or any other key) survives the mapping.
assert provider_tools_to_anthropic_tools([{"type": "web_search", "max_uses": 3}]) == [
{"type": "web_search_20250305", "name": "web_search", "max_uses": 3}
]
# An entry that already names the surface's tool passes through.
assert provider_tools_to_anthropic_tools([{"type": "web_search_20260209", "name": "web_search"}]) == [
{"type": "web_search_20260209", "name": "web_search"}
]
# Entries without a type are dropped (nothing to declare on the wire).
assert provider_tools_to_anthropic_tools([{"name": "web_search"}]) == []
def test_chat_param_to_anthropic_param_merges_provider_tools_after_local_ones() -> None:
param = ChatCompletionsParam(
model="deepseek-flash",
messages=[UserChatMessage(content="hi")],
tools=[
ToolFunctionItem(
function=ToolFunction(
name="read_file",
description="Read a file.",
parameters={"type": "object", "properties": {}},
)
)
],
)
built = chat_param_to_anthropic_param(param, provider_tools=[{"type": "web_search"}])
tools = built.tools
assert tools is not UNSET
assert isinstance(tools[0], AnthropicToolDefinition)
assert tools[0].name == "read_file"
assert tools[1] == {"type": "web_search_20250305", "name": "web_search"}
def test_anthropic_response_to_chat_completion_usage() -> None:
response = AnthropicMessageResponse(
id="msg_1",
+104
View File
@@ -20,6 +20,7 @@ from plyngent.agent.messages_dispatch import dispatch_messages
from plyngent.lmproto.anthropic.model import (
AnthropicContentBlockDelta,
AnthropicContentBlockStart,
AnthropicContentBlockStop,
AnthropicMessageDelta,
AnthropicMessageResponse,
AnthropicMessagesParam,
@@ -393,3 +394,106 @@ async def test_dispatch_stream_tool_calls_without_stop_yields_no_finish() -> Non
chunks = [chunk async for chunk in cast("Any", stream)]
# tool-call start delta only; no fabricated finish_reason=tool_calls
assert not any(c.choices and c.choices[0].finish_reason not in (None, UNSET) for c in chunks)
def _search_stream_events() -> list[AnthropicStreamEvent]:
"""The stream a DeepSeek search turn sends: thinking, search, results, text."""
return [
AnthropicMessageStart(
message=AnthropicMessageResponse(
id="msg_s",
model="deepseek-flash",
content=[],
usage=AnthropicUsage(input_tokens=164, output_tokens=0),
)
),
AnthropicContentBlockStart(index=0, content_block=AnthropicRawContentBlock(type="thinking", text="")),
AnthropicContentBlockDelta(
index=0,
delta=AnthropicRawContentBlock(type="thinking_delta", text="Search."),
),
AnthropicContentBlockStop(index=0),
AnthropicContentBlockStart(
index=1,
content_block=AnthropicRawContentBlock(type="server_tool_use", id="call_00_1", name="web_search", input={}),
),
AnthropicContentBlockDelta(
index=1,
delta=AnthropicRawContentBlock(type="input_json_delta", partial_json='{"query":'),
),
AnthropicContentBlockDelta(
index=1,
delta=AnthropicRawContentBlock(type="input_json_delta", partial_json='"DeepSeek-V4"}'),
),
AnthropicContentBlockStop(index=1),
AnthropicContentBlockStart(
index=2,
content_block=AnthropicRawContentBlock(
type="web_search_tool_result",
id="call_00_1",
input={"content": [{"type": "web_search_result", "url": "https://api-docs.deepseek.com"}]},
),
),
AnthropicContentBlockStop(index=2),
AnthropicContentBlockStart(index=3, content_block=AnthropicRawContentBlock(type="text", text="")),
AnthropicContentBlockDelta(
index=3,
delta=AnthropicRawContentBlock(type="text_delta", text="DeepSeek-V4 is out."),
),
AnthropicContentBlockStop(index=3),
AnthropicMessageDelta(
delta={"stop_reason": "end_turn"},
usage=AnthropicUsage(input_tokens=0, output_tokens=12),
),
AnthropicMessageStop(),
]
async def test_search_turn_streams_its_text_without_a_local_tool_call() -> None:
"""A server tool's arguments must not become a call for the registry.
DeepSeek streams a ``server_tool_use`` block whose ``input_json_delta``
fragments carry the search query. Reading those as a local call's arguments
asks the registry for a tool the *server* already ran — and would have the
agent execute ``web_search`` (or a nameless tool) itself.
"""
client = ScriptedMessagesClient(stream_events=[_search_stream_events()])
@tool(register=False)
def echo(text: str) -> str:
return text
events = [
event
async for event in run_chat_loop(
cast("Any", client),
[UserChatMessage(content="what is DeepSeek-V4?")],
model="deepseek-flash",
tools=ToolRegistry([echo]),
stream=True,
)
]
assert not any(isinstance(event, ToolCallEvent) for event in events)
assert not any(isinstance(event, ToolResultEvent) for event in events)
assert any(isinstance(event, TextDeltaEvent) and event.content == "DeepSeek-V4 is out." for event in events)
# One round: the search answered inside the response, so nothing was sent back.
assert len(client.calls) == 1
async def test_dispatch_messages_sends_provider_tools_as_server_tools() -> None:
"""Hosted tools reach the Anthropic request in that surface's own shape."""
client = ScriptedMessagesClient(non_stream=[_message_response(text="ok")])
param = ChatCompletionsParam(model="deepseek-flash", messages=[UserChatMessage(content="hi")])
_ = await dispatch_messages(
cast("Any", client),
param,
provider_tools=[{"type": "web_search", "max_uses": 3}],
)
assert client.calls[0].tools == [{"type": "web_search_20250305", "name": "web_search", "max_uses": 3}]
async def test_dispatch_messages_without_provider_tools_sends_no_server_tool() -> None:
client = ScriptedMessagesClient(non_stream=[_message_response(text="ok")])
param = ChatCompletionsParam(model="deepseek-flash", messages=[UserChatMessage(content="hi")])
_ = await dispatch_messages(cast("Any", client), param, provider_tools=[])
assert client.calls[0].tools is UNSET
+70
View File
@@ -13,6 +13,7 @@ from plyngent.lmproto.anthropic.model import (
AnthropicResponseText,
AnthropicUsage,
AnthropicUserMessage,
AnthropicWebSearchToolResultContent,
)
@@ -44,6 +45,75 @@ def test_messages_param_encode_omits_defaults() -> None:
@pytest.mark.asyncio
async def test_client_decodes_a_server_side_search_response(monkeypatch: pytest.MonkeyPatch) -> None:
"""DeepSeek's Anthropic compat answers a search turn with server tool blocks.
A live turn reads ``thinking, server_tool_use, web_search_tool_result, text``
(the results carry an ``encrypted_content`` the API demands back unchanged);
the response must decode, even though none of those blocks is a local call.
"""
body = {
"id": "msg_search",
"type": "message",
"role": "assistant",
"model": "deepseek-flash",
"stop_reason": "end_turn",
"content": [
{"type": "thinking", "thinking": "Let me search.", "signature": "b032a4ad-87fe-42ce-801d-e33dd743d8b9"},
{
"type": "server_tool_use",
"id": "call_00_joE6PEEC1otU8pvSe4zY3017",
"name": "web_search",
"input": {"query": "DeepSeek latest news"},
"caller": {"type": "direct"},
},
{
"type": "web_search_tool_result",
"tool_use_id": "call_00_joE6PEEC1otU8pvSe4zY3017",
"content": [
{
"type": "web_search_result",
"title": "Change Log | DeepSeek API Docs",
"url": "https://api-docs.deepseek.com/updates/",
"encrypted_content": "sd918tZXSvVp6j7ermvF4cl/lspbqHzths9SMQw6ziEw",
}
],
},
{"type": "text", "text": "DeepSeek shipped a new model."},
],
"usage": {"input_tokens": 16592, "output_tokens": 1419, "server_tool_use": {"web_search_requests": 4}},
}
client = AnthropicClient(AnthropicConfig(api_key="sk-test", base_url="https://example/v1"))
class _Resp:
status_code = 200
content = msgspec.json.encode(body)
async def fake_post(path: str, **kwargs: object) -> _Resp:
return _Resp()
monkeypatch.setattr(client.session, "post", fake_post)
result = await client.messages(AnthropicMessagesParam(model="deepseek-flash", messages=[]))
kinds = [block.__struct_config__.tag for block in result.content]
assert kinds == ["thinking", "server_tool_use", "web_search_tool_result", "text"]
search = result.content[2]
assert isinstance(search, AnthropicWebSearchToolResultContent)
assert search.tool_use_id == "call_00_joE6PEEC1otU8pvSe4zY3017"
assert search.content[0]["encrypted_content"].startswith("sd918tZXSvVp")
assert result.content[3].text == "DeepSeek shipped a new model."
def test_messages_param_encodes_server_tool_dicts() -> None:
"""A hosted tool goes on the wire as the server-tool dict the surface wants."""
param = AnthropicMessagesParam(
model="deepseek-flash",
messages=[AnthropicUserMessage(content="hi")],
tools=[{"type": "web_search_20250305", "name": "web_search", "max_uses": 3}],
)
data = msgspec.json.decode(msgspec.json.encode(param))
assert data["tools"] == [{"type": "web_search_20250305", "name": "web_search", "max_uses": 3}]
async def test_client_messages_create(monkeypatch: pytest.MonkeyPatch) -> None:
client = AnthropicClient(AnthropicConfig(api_key="sk-test", base_url="https://example/v1"))