Compare commits

..

1 Commits

Author SHA1 Message Date
Alexander Whitestone
d1fb50bf2f feat: add Anthropic transport abstraction slice (#951)
All checks were successful
Lint / lint (pull_request) Successful in 8s
- add transport registry, shared transport dataclasses, and AnthropicTransport
- add normalize_anthropic_response_v2 as the bridge from existing Anthropic normalization to shared transport types
- extend Anthropic stop-reason mapping for refusal and model_context_window_exceeded
- add targeted transport and v2 normalization regression tests

Closes #951
Refs #949
2026-04-22 11:20:20 -04:00
15 changed files with 873 additions and 467 deletions

View File

@@ -1396,6 +1396,8 @@ def normalize_anthropic_response(
"tool_use": "tool_calls",
"max_tokens": "length",
"stop_sequence": "stop",
"refusal": "content_filter",
"model_context_window_exceeded": "length",
}
finish_reason = stop_reason_map.get(response.stop_reason, "stop")
@@ -1409,3 +1411,42 @@ def normalize_anthropic_response(
),
finish_reason,
)
def normalize_anthropic_response_v2(
response,
strip_tool_prefix: bool = False,
) -> "NormalizedResponse":
"""Normalize Anthropic response to NormalizedResponse.
Wraps the existing normalize_anthropic_response() and maps its output
to the shared transport types. This allows incremental migration
without disturbing the legacy call sites.
"""
from agent.transports.types import NormalizedResponse, build_tool_call
assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
tool_calls = None
if assistant_msg.tool_calls:
tool_calls = [
build_tool_call(
id=tc.id,
name=tc.function.name,
arguments=tc.function.arguments,
)
for tc in assistant_msg.tool_calls
]
provider_data = {}
if getattr(assistant_msg, "reasoning_details", None):
provider_data["reasoning_details"] = assistant_msg.reasoning_details
return NormalizedResponse(
content=assistant_msg.content,
tool_calls=tool_calls,
finish_reason=finish_reason,
reasoning=getattr(assistant_msg, "reasoning", None),
usage=None,
provider_data=provider_data or None,
)

View File

@@ -0,0 +1,57 @@
"""Transport layer types and registry for provider response normalization.
Usage:
from agent.transports import get_transport
transport = get_transport("anthropic_messages")
result = transport.normalize_response(raw_response)
"""
from agent.transports.types import ( # noqa: F401
NormalizedResponse,
ToolCall,
Usage,
build_tool_call,
map_finish_reason,
)
_REGISTRY: dict = {}
def register_transport(api_mode: str, transport_cls: type) -> None:
"""Register a transport class for an api_mode string."""
_REGISTRY[api_mode] = transport_cls
def get_transport(api_mode: str):
"""Get a transport instance for the given api_mode.
Returns None if no transport is registered for this api_mode.
This allows gradual migration — call sites can check for None
and fall back to the legacy code path.
"""
if not _REGISTRY:
_discover_transports()
cls = _REGISTRY.get(api_mode)
if cls is None:
return None
return cls()
def _discover_transports() -> None:
"""Import all transport modules to trigger auto-registration."""
try:
import agent.transports.anthropic # noqa: F401
except ImportError:
pass
try:
import agent.transports.codex # noqa: F401
except ImportError:
pass
try:
import agent.transports.chat_completions # noqa: F401
except ImportError:
pass
try:
import agent.transports.bedrock # noqa: F401
except ImportError:
pass

View File

@@ -0,0 +1,95 @@
"""Anthropic Messages API transport.
Delegates to the existing adapter functions in agent/anthropic_adapter.py.
This transport owns format conversion and normalization — NOT client lifecycle.
"""
from typing import Any, Dict, List, Optional
from agent.transports.base import ProviderTransport
from agent.transports.types import NormalizedResponse
class AnthropicTransport(ProviderTransport):
"""Transport for api_mode='anthropic_messages'."""
@property
def api_mode(self) -> str:
return "anthropic_messages"
def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
from agent.anthropic_adapter import convert_messages_to_anthropic
base_url = kwargs.get("base_url")
return convert_messages_to_anthropic(messages, base_url=base_url)
def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
from agent.anthropic_adapter import convert_tools_to_anthropic
return convert_tools_to_anthropic(tools)
def build_kwargs(
self,
model: str,
messages: List[Dict[str, Any]],
tools: Optional[List[Dict[str, Any]]] = None,
**params,
) -> Dict[str, Any]:
from agent.anthropic_adapter import build_anthropic_kwargs
return build_anthropic_kwargs(
model=model,
messages=messages,
tools=tools,
max_tokens=params.get("max_tokens", 16384),
reasoning_config=params.get("reasoning_config"),
tool_choice=params.get("tool_choice"),
is_oauth=params.get("is_oauth", False),
preserve_dots=params.get("preserve_dots", False),
context_length=params.get("context_length"),
base_url=params.get("base_url"),
fast_mode=params.get("fast_mode", False),
)
def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
from agent.anthropic_adapter import normalize_anthropic_response_v2
strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
return normalize_anthropic_response_v2(response, strip_tool_prefix=strip_tool_prefix)
def validate_response(self, response: Any) -> bool:
if response is None:
return False
content_blocks = getattr(response, "content", None)
if not isinstance(content_blocks, list):
return False
if not content_blocks:
return False
return True
def extract_cache_stats(self, response: Any):
usage = getattr(response, "usage", None)
if usage is None:
return None
cached = getattr(usage, "cache_read_input_tokens", 0) or 0
written = getattr(usage, "cache_creation_input_tokens", 0) or 0
if cached or written:
return {"cached_tokens": cached, "creation_tokens": written}
return None
_STOP_REASON_MAP = {
"end_turn": "stop",
"tool_use": "tool_calls",
"max_tokens": "length",
"stop_sequence": "stop",
"refusal": "content_filter",
"model_context_window_exceeded": "length",
}
def map_finish_reason(self, raw_reason: str) -> str:
return self._STOP_REASON_MAP.get(raw_reason, "stop")
from agent.transports import register_transport # noqa: E402
register_transport("anthropic_messages", AnthropicTransport)

61
agent/transports/base.py Normal file
View File

@@ -0,0 +1,61 @@
"""Abstract base for provider transports.
A transport owns the data path for one api_mode:
convert_messages → convert_tools → build_kwargs → normalize_response
It does NOT own: client construction, streaming, credential refresh,
prompt caching, interrupt handling, or retry logic. Those stay on AIAgent.
"""
from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional
from agent.transports.types import NormalizedResponse
class ProviderTransport(ABC):
"""Base class for provider-specific format conversion and normalization."""
@property
@abstractmethod
def api_mode(self) -> str:
"""The api_mode string this transport handles."""
...
@abstractmethod
def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
"""Convert OpenAI-format messages to provider-native format."""
...
@abstractmethod
def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
"""Convert OpenAI-format tool definitions to provider-native format."""
...
@abstractmethod
def build_kwargs(
self,
model: str,
messages: List[Dict[str, Any]],
tools: Optional[List[Dict[str, Any]]] = None,
**params,
) -> Dict[str, Any]:
"""Build the complete provider kwargs dict."""
...
@abstractmethod
def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
"""Normalize a raw provider response to the shared NormalizedResponse type."""
...
def validate_response(self, response: Any) -> bool:
"""Optional structural validation for raw responses."""
return True
def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
"""Optional cache stats extraction."""
return None
def map_finish_reason(self, raw_reason: str) -> str:
"""Optional stop-reason mapping. Defaults to passthrough."""
return raw_reason

58
agent/transports/types.py Normal file
View File

@@ -0,0 +1,58 @@
"""Shared types for normalized provider responses."""
from __future__ import annotations
import json
from dataclasses import dataclass, field
from typing import Any, Dict, List, Optional
@dataclass
class ToolCall:
"""A normalized tool call from any provider."""
id: Optional[str]
name: str
arguments: str
provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
@dataclass
class Usage:
"""Token usage from an API response."""
prompt_tokens: int = 0
completion_tokens: int = 0
total_tokens: int = 0
cached_tokens: int = 0
@dataclass
class NormalizedResponse:
"""Normalized API response from any provider."""
content: Optional[str]
tool_calls: Optional[List[ToolCall]]
finish_reason: str
reasoning: Optional[str] = None
usage: Optional[Usage] = None
provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
def build_tool_call(
id: Optional[str],
name: str,
arguments: Any,
**provider_fields: Any,
) -> ToolCall:
"""Build a ToolCall, auto-serialising dict arguments."""
args_str = json.dumps(arguments) if isinstance(arguments, dict) else str(arguments)
provider_data = dict(provider_fields) if provider_fields else None
return ToolCall(id=id, name=name, arguments=args_str, provider_data=provider_data)
def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
"""Translate a provider-specific stop reason to the normalized set."""
if reason is None:
return "stop"
return mapping.get(reason, "stop")

View File

@@ -0,0 +1,213 @@
"""Regression tests: normalize_anthropic_response_v2 vs v1.
Constructs mock Anthropic responses and asserts that the v2 function
(returning NormalizedResponse) produces identical field values to the
original v1 function (returning SimpleNamespace + finish_reason).
"""
from types import SimpleNamespace
import pytest
from agent.anthropic_adapter import (
normalize_anthropic_response,
normalize_anthropic_response_v2,
)
from agent.transports.types import NormalizedResponse
def _text_block(text: str):
return SimpleNamespace(type="text", text=text)
def _thinking_block(thinking: str, signature: str = "sig_abc"):
return SimpleNamespace(type="thinking", thinking=thinking, signature=signature)
def _tool_use_block(id: str, name: str, input: dict):
return SimpleNamespace(type="tool_use", id=id, name=name, input=input)
def _response(content_blocks, stop_reason="end_turn"):
return SimpleNamespace(
content=content_blocks,
stop_reason=stop_reason,
usage=SimpleNamespace(input_tokens=10, output_tokens=5),
)
class TestTextOnly:
def setup_method(self):
self.resp = _response([_text_block("Hello world")])
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
self.v2 = normalize_anthropic_response_v2(self.resp)
def test_type(self):
assert isinstance(self.v2, NormalizedResponse)
def test_content_matches(self):
assert self.v2.content == self.v1_msg.content
def test_finish_reason_matches(self):
assert self.v2.finish_reason == self.v1_finish
def test_no_tool_calls(self):
assert self.v2.tool_calls is None
assert self.v1_msg.tool_calls is None
def test_no_reasoning(self):
assert self.v2.reasoning is None
assert self.v1_msg.reasoning is None
class TestWithToolCalls:
def setup_method(self):
self.resp = _response(
[
_text_block("I'll check that"),
_tool_use_block("toolu_abc", "terminal", {"command": "ls"}),
_tool_use_block("toolu_def", "read_file", {"path": "/tmp"}),
],
stop_reason="tool_use",
)
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
self.v2 = normalize_anthropic_response_v2(self.resp)
def test_finish_reason(self):
assert self.v2.finish_reason == "tool_calls"
assert self.v1_finish == "tool_calls"
def test_tool_call_count(self):
assert len(self.v2.tool_calls) == 2
assert len(self.v1_msg.tool_calls) == 2
def test_tool_call_ids_match(self):
for i in range(2):
assert self.v2.tool_calls[i].id == self.v1_msg.tool_calls[i].id
def test_tool_call_names_match(self):
assert self.v2.tool_calls[0].name == "terminal"
assert self.v2.tool_calls[1].name == "read_file"
for i in range(2):
assert self.v2.tool_calls[i].name == self.v1_msg.tool_calls[i].function.name
def test_tool_call_arguments_match(self):
for i in range(2):
assert self.v2.tool_calls[i].arguments == self.v1_msg.tool_calls[i].function.arguments
def test_content_preserved(self):
assert self.v2.content == self.v1_msg.content
assert "check that" in self.v2.content
class TestWithThinking:
def setup_method(self):
self.resp = _response([
_thinking_block("Let me think about this carefully..."),
_text_block("The answer is 42."),
])
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
self.v2 = normalize_anthropic_response_v2(self.resp)
def test_reasoning_matches(self):
assert self.v2.reasoning == self.v1_msg.reasoning
assert "think about this" in self.v2.reasoning
def test_reasoning_details_in_provider_data(self):
v1_details = self.v1_msg.reasoning_details
v2_details = self.v2.provider_data.get("reasoning_details") if self.v2.provider_data else None
assert v1_details is not None
assert v2_details is not None
assert len(v2_details) == len(v1_details)
def test_content_excludes_thinking(self):
assert self.v2.content == "The answer is 42."
class TestMixed:
def setup_method(self):
self.resp = _response(
[
_thinking_block("Planning my approach..."),
_text_block("I'll run the command"),
_tool_use_block("toolu_xyz", "terminal", {"command": "pwd"}),
],
stop_reason="tool_use",
)
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
self.v2 = normalize_anthropic_response_v2(self.resp)
def test_all_fields_present(self):
assert self.v2.content is not None
assert self.v2.tool_calls is not None
assert self.v2.reasoning is not None
assert self.v2.finish_reason == "tool_calls"
def test_content_matches(self):
assert self.v2.content == self.v1_msg.content
def test_reasoning_matches(self):
assert self.v2.reasoning == self.v1_msg.reasoning
def test_tool_call_matches(self):
assert self.v2.tool_calls[0].id == self.v1_msg.tool_calls[0].id
assert self.v2.tool_calls[0].name == self.v1_msg.tool_calls[0].function.name
class TestStopReasons:
@pytest.mark.parametrize("stop_reason,expected", [
("end_turn", "stop"),
("tool_use", "tool_calls"),
("max_tokens", "length"),
("stop_sequence", "stop"),
("refusal", "content_filter"),
("model_context_window_exceeded", "length"),
("unknown_future_reason", "stop"),
])
def test_stop_reason_mapping(self, stop_reason, expected):
resp = _response([_text_block("x")], stop_reason=stop_reason)
_v1_msg, v1_finish = normalize_anthropic_response(resp)
v2 = normalize_anthropic_response_v2(resp)
assert v2.finish_reason == v1_finish == expected
class TestStripToolPrefix:
def test_prefix_stripped(self):
resp = _response(
[_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
stop_reason="tool_use",
)
v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=True)
v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=True)
assert v1_msg.tool_calls[0].function.name == "terminal"
assert v2.tool_calls[0].name == "terminal"
def test_prefix_kept(self):
resp = _response(
[_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
stop_reason="tool_use",
)
v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=False)
v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=False)
assert v1_msg.tool_calls[0].function.name == "mcp_terminal"
assert v2.tool_calls[0].name == "mcp_terminal"
class TestEdgeCases:
def test_empty_content_blocks(self):
resp = _response([])
v1_msg, _v1_finish = normalize_anthropic_response(resp)
v2 = normalize_anthropic_response_v2(resp)
assert v2.content == v1_msg.content
assert v2.content is None
def test_no_reasoning_details_means_none_provider_data(self):
resp = _response([_text_block("hi")])
v2 = normalize_anthropic_response_v2(resp)
assert v2.provider_data is None
def test_v2_returns_dataclass_not_namespace(self):
resp = _response([_text_block("hi")])
v2 = normalize_anthropic_response_v2(resp)
assert isinstance(v2, NormalizedResponse)
assert not isinstance(v2, SimpleNamespace)

View File

@@ -0,0 +1,208 @@
"""Tests for the transport ABC, registry, and AnthropicTransport."""
from types import SimpleNamespace
import pytest
from agent.transports import _REGISTRY, get_transport, register_transport
from agent.transports.base import ProviderTransport
from agent.transports.types import NormalizedResponse
class TestProviderTransportABC:
def test_cannot_instantiate_abc(self):
with pytest.raises(TypeError):
ProviderTransport()
def test_concrete_must_implement_all_abstract(self):
class Incomplete(ProviderTransport):
@property
def api_mode(self):
return "test"
with pytest.raises(TypeError):
Incomplete()
def test_minimal_concrete(self):
class Minimal(ProviderTransport):
@property
def api_mode(self):
return "test_minimal"
def convert_messages(self, messages, **kw):
return messages
def convert_tools(self, tools):
return tools
def build_kwargs(self, model, messages, tools=None, **params):
return {"model": model, "messages": messages}
def normalize_response(self, response, **kw):
return NormalizedResponse(content="ok", tool_calls=None, finish_reason="stop")
t = Minimal()
assert t.api_mode == "test_minimal"
assert t.validate_response(None) is True
assert t.extract_cache_stats(None) is None
assert t.map_finish_reason("end_turn") == "end_turn"
class TestTransportRegistry:
def test_get_unregistered_returns_none(self):
assert get_transport("nonexistent_mode") is None
def test_anthropic_registered_on_import(self):
import agent.transports.anthropic # noqa: F401
t = get_transport("anthropic_messages")
assert t is not None
assert t.api_mode == "anthropic_messages"
def test_register_and_get(self):
class DummyTransport(ProviderTransport):
@property
def api_mode(self):
return "dummy_test"
def convert_messages(self, messages, **kw):
return messages
def convert_tools(self, tools):
return tools
def build_kwargs(self, model, messages, tools=None, **params):
return {}
def normalize_response(self, response, **kw):
return NormalizedResponse(content=None, tool_calls=None, finish_reason="stop")
register_transport("dummy_test", DummyTransport)
t = get_transport("dummy_test")
assert t.api_mode == "dummy_test"
_REGISTRY.pop("dummy_test", None)
class TestAnthropicTransport:
@pytest.fixture
def transport(self):
import agent.transports.anthropic # noqa: F401
return get_transport("anthropic_messages")
def test_api_mode(self, transport):
assert transport.api_mode == "anthropic_messages"
def test_convert_tools_simple(self, transport):
tools = [{
"type": "function",
"function": {
"name": "test_tool",
"description": "A test",
"parameters": {"type": "object", "properties": {}},
},
}]
result = transport.convert_tools(tools)
assert len(result) == 1
assert result[0]["name"] == "test_tool"
assert "input_schema" in result[0]
def test_validate_response_none(self, transport):
assert transport.validate_response(None) is False
def test_validate_response_empty_content(self, transport):
r = SimpleNamespace(content=[])
assert transport.validate_response(r) is False
def test_validate_response_valid(self, transport):
r = SimpleNamespace(content=[SimpleNamespace(type="text", text="hello")])
assert transport.validate_response(r) is True
def test_map_finish_reason(self, transport):
assert transport.map_finish_reason("end_turn") == "stop"
assert transport.map_finish_reason("tool_use") == "tool_calls"
assert transport.map_finish_reason("max_tokens") == "length"
assert transport.map_finish_reason("stop_sequence") == "stop"
assert transport.map_finish_reason("refusal") == "content_filter"
assert transport.map_finish_reason("model_context_window_exceeded") == "length"
assert transport.map_finish_reason("unknown") == "stop"
def test_extract_cache_stats_none_usage(self, transport):
r = SimpleNamespace(usage=None)
assert transport.extract_cache_stats(r) is None
def test_extract_cache_stats_with_cache(self, transport):
usage = SimpleNamespace(cache_read_input_tokens=100, cache_creation_input_tokens=50)
r = SimpleNamespace(usage=usage)
result = transport.extract_cache_stats(r)
assert result == {"cached_tokens": 100, "creation_tokens": 50}
def test_extract_cache_stats_zero(self, transport):
usage = SimpleNamespace(cache_read_input_tokens=0, cache_creation_input_tokens=0)
r = SimpleNamespace(usage=usage)
assert transport.extract_cache_stats(r) is None
def test_normalize_response_text(self, transport):
r = SimpleNamespace(
content=[SimpleNamespace(type="text", text="Hello world")],
stop_reason="end_turn",
usage=SimpleNamespace(input_tokens=10, output_tokens=5),
model="claude-sonnet-4-6",
)
nr = transport.normalize_response(r)
assert isinstance(nr, NormalizedResponse)
assert nr.content == "Hello world"
assert nr.tool_calls is None or nr.tool_calls == []
assert nr.finish_reason == "stop"
def test_normalize_response_tool_calls(self, transport):
r = SimpleNamespace(
content=[
SimpleNamespace(type="tool_use", id="toolu_123", name="terminal", input={"command": "ls"}),
],
stop_reason="tool_use",
usage=SimpleNamespace(input_tokens=10, output_tokens=20),
model="claude-sonnet-4-6",
)
nr = transport.normalize_response(r)
assert nr.finish_reason == "tool_calls"
assert len(nr.tool_calls) == 1
tc = nr.tool_calls[0]
assert tc.name == "terminal"
assert tc.id == "toolu_123"
assert '"command"' in tc.arguments
def test_normalize_response_thinking(self, transport):
r = SimpleNamespace(
content=[
SimpleNamespace(type="thinking", thinking="Let me think..."),
SimpleNamespace(type="text", text="The answer is 42"),
],
stop_reason="end_turn",
usage=SimpleNamespace(input_tokens=10, output_tokens=15),
model="claude-sonnet-4-6",
)
nr = transport.normalize_response(r)
assert nr.content == "The answer is 42"
assert nr.reasoning == "Let me think..."
def test_build_kwargs_returns_dict(self, transport):
messages = [{"role": "user", "content": "Hello"}]
kw = transport.build_kwargs(
model="claude-sonnet-4-6",
messages=messages,
max_tokens=1024,
)
assert isinstance(kw, dict)
assert "model" in kw
assert "max_tokens" in kw
assert "messages" in kw
def test_convert_messages_extracts_system(self, transport):
messages = [
{"role": "system", "content": "You are helpful."},
{"role": "user", "content": "Hi"},
]
system, msgs = transport.convert_messages(messages)
assert system is not None
assert len(msgs) >= 1

View File

@@ -0,0 +1,130 @@
"""Tests for agent/transports/types.py — dataclass construction + helpers."""
import json
from agent.transports.types import (
NormalizedResponse,
ToolCall,
Usage,
build_tool_call,
map_finish_reason,
)
class TestToolCall:
def test_basic_construction(self):
tc = ToolCall(id="call_abc", name="terminal", arguments='{"cmd": "ls"}')
assert tc.id == "call_abc"
assert tc.name == "terminal"
assert tc.arguments == '{"cmd": "ls"}'
assert tc.provider_data is None
def test_none_id(self):
tc = ToolCall(id=None, name="read_file", arguments="{}")
assert tc.id is None
def test_provider_data(self):
tc = ToolCall(
id="call_x",
name="t",
arguments="{}",
provider_data={"call_id": "call_x", "response_item_id": "fc_x"},
)
assert tc.provider_data["call_id"] == "call_x"
assert tc.provider_data["response_item_id"] == "fc_x"
class TestUsage:
def test_defaults(self):
u = Usage()
assert u.prompt_tokens == 0
assert u.completion_tokens == 0
assert u.total_tokens == 0
assert u.cached_tokens == 0
def test_explicit(self):
u = Usage(prompt_tokens=100, completion_tokens=50, total_tokens=150, cached_tokens=80)
assert u.total_tokens == 150
class TestNormalizedResponse:
def test_text_only(self):
r = NormalizedResponse(content="hello", tool_calls=None, finish_reason="stop")
assert r.content == "hello"
assert r.tool_calls is None
assert r.finish_reason == "stop"
assert r.reasoning is None
assert r.usage is None
assert r.provider_data is None
def test_with_tool_calls(self):
tcs = [ToolCall(id="call_1", name="terminal", arguments='{"cmd":"pwd"}')]
r = NormalizedResponse(content=None, tool_calls=tcs, finish_reason="tool_calls")
assert r.finish_reason == "tool_calls"
assert len(r.tool_calls) == 1
assert r.tool_calls[0].name == "terminal"
def test_with_reasoning(self):
r = NormalizedResponse(
content="answer",
tool_calls=None,
finish_reason="stop",
reasoning="I thought about it",
)
assert r.reasoning == "I thought about it"
def test_with_provider_data(self):
r = NormalizedResponse(
content=None,
tool_calls=None,
finish_reason="stop",
provider_data={"reasoning_details": [{"type": "thinking", "thinking": "hmm"}]},
)
assert r.provider_data["reasoning_details"][0]["type"] == "thinking"
class TestBuildToolCall:
def test_dict_arguments_serialized(self):
tc = build_tool_call(id="call_1", name="terminal", arguments={"cmd": "ls"})
assert tc.arguments == json.dumps({"cmd": "ls"})
assert tc.provider_data is None
def test_string_arguments_passthrough(self):
tc = build_tool_call(id="call_2", name="read_file", arguments='{"path": "/tmp"}')
assert tc.arguments == '{"path": "/tmp"}'
def test_provider_fields(self):
tc = build_tool_call(
id="call_3",
name="terminal",
arguments="{}",
call_id="call_3",
response_item_id="fc_3",
)
assert tc.provider_data == {"call_id": "call_3", "response_item_id": "fc_3"}
def test_none_id(self):
tc = build_tool_call(id=None, name="t", arguments="{}")
assert tc.id is None
class TestMapFinishReason:
ANTHROPIC_MAP = {
"end_turn": "stop",
"tool_use": "tool_calls",
"max_tokens": "length",
"stop_sequence": "stop",
"refusal": "content_filter",
}
def test_known_reason(self):
assert map_finish_reason("end_turn", self.ANTHROPIC_MAP) == "stop"
assert map_finish_reason("tool_use", self.ANTHROPIC_MAP) == "tool_calls"
assert map_finish_reason("max_tokens", self.ANTHROPIC_MAP) == "length"
assert map_finish_reason("refusal", self.ANTHROPIC_MAP) == "content_filter"
def test_unknown_reason_defaults_to_stop(self):
assert map_finish_reason("something_new", self.ANTHROPIC_MAP) == "stop"
def test_none_reason(self):
assert map_finish_reason(None, self.ANTHROPIC_MAP) == "stop"

View File

@@ -148,184 +148,3 @@ class TestStrategyNameSurfaced:
assert count == 0
assert strategy is None
assert err is not None
class TestEscapeDriftGuard:
"""Tests for the escape-drift guard that catches bash/JSON serialization
artifacts where an apostrophe gets prefixed with a spurious backslash
in tool-call transport.
"""
def test_drift_blocked_apostrophe(self):
"""File has ', old_string and new_string both have \\' — classic
tool-call drift. Guard must block with a helpful error instead of
writing \\' literals into source code."""
content = "x = \"hello there\"\n"
# Simulate transport-corrupted old_string and new_string where an
# apostrophe-like context got prefixed with a backslash. The content
# itself has no apostrophe, but both strings do — matching via
# whitespace/anchor strategies would otherwise succeed.
old_string = "x = \"hello there\" # don\\'t edit\n"
new_string = "x = \"hi there\" # don\\'t edit\n"
# This particular pair won't match anything, so it exits via
# no-match path. Build a case where a non-exact strategy DOES match.
content = "line\n x = 1\nline"
old_string = "line\n x = \\'a\\'\nline"
new_string = "line\n x = \\'b\\'\nline"
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
assert count == 0
assert err is not None and "Escape-drift" in err
assert "backslash" in err.lower()
assert new == content # file untouched
def test_drift_blocked_double_quote(self):
"""Same idea but with \\" drift instead of \\'."""
content = 'line\n x = 1\nline'
old_string = 'line\n x = \\"a\\"\nline'
new_string = 'line\n x = \\"b\\"\nline'
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
assert count == 0
assert err is not None and "Escape-drift" in err
def test_drift_allowed_when_file_genuinely_has_backslash_escapes(self):
"""If the file already contains \\' (e.g. inside an existing escaped
string), the model is legitimately preserving it. Guard must NOT
fire."""
content = "line\n x = \\'a\\'\nline"
old_string = "line\n x = \\'a\\'\nline"
new_string = "line\n x = \\'b\\'\nline"
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
assert err is None
assert count == 1
assert "\\'b\\'" in new
def test_drift_allowed_on_exact_match(self):
"""Exact matches bypass the drift guard entirely — if the file
really contains the exact bytes old_string specified, it's not
drift."""
content = "hello \\'world\\'"
new, count, strategy, err = fuzzy_find_and_replace(
content, "hello \\'world\\'", "hello \\'there\\'"
)
assert err is None
assert count == 1
assert strategy == "exact"
def test_drift_allowed_when_adding_escaped_strings(self):
"""Model is adding new content with \\' that wasn't in the original.
old_string has no \\', so guard doesn't fire."""
content = "line1\nline2\nline3"
old_string = "line1\nline2\nline3"
new_string = "line1\nprint(\\'added\\')\nline2\nline3"
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
assert err is None
assert count == 1
assert "\\'added\\'" in new
def test_no_drift_check_when_new_string_lacks_suspect_chars(self):
"""Fast-path: if new_string has no \\' or \\", guard must not
fire even on fuzzy match."""
content = "def foo():\n pass" # extra space ignored by line_trimmed
old_string = "def foo():\n pass"
new_string = "def bar():\n return 1"
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
assert err is None
assert count == 1
class TestFindClosestLines:
def setup_method(self):
from tools.fuzzy_match import find_closest_lines
self.find_closest_lines = find_closest_lines
def test_finds_similar_line(self):
content = "def foo():\n pass\ndef bar():\n return 1\n"
result = self.find_closest_lines("def baz():", content)
assert "def foo" in result or "def bar" in result
def test_returns_empty_for_no_match(self):
content = "completely different content here"
result = self.find_closest_lines("xyzzy_no_match_possible_!!!", content)
assert result == ""
def test_returns_empty_for_empty_inputs(self):
assert self.find_closest_lines("", "some content") == ""
assert self.find_closest_lines("old string", "") == ""
def test_includes_context_lines(self):
content = "line1\nline2\ndef target():\n pass\nline5\n"
result = self.find_closest_lines("def target():", content)
assert "target" in result
def test_includes_line_numbers(self):
content = "line1\nline2\ndef foo():\n pass\n"
result = self.find_closest_lines("def foo():", content)
# Should include line numbers in format "N| content"
assert "|" in result
class TestFormatNoMatchHint:
"""Gating tests for format_no_match_hint — the shared helper that decides
whether a 'Did you mean?' snippet should be appended to an error.
"""
def setup_method(self):
from tools.fuzzy_match import format_no_match_hint
self.fmt = format_no_match_hint
def test_fires_on_could_not_find_with_match(self):
"""Classic no-match: similar content exists → hint fires."""
content = "def foo():\n pass\ndef bar():\n pass\n"
result = self.fmt(
"Could not find a match for old_string in the file",
0, "def baz():", content,
)
assert "Did you mean" in result
assert "foo" in result or "bar" in result
def test_silent_on_ambiguous_match_error(self):
"""'Found N matches' is not a missing-match failure — no hint."""
content = "aaa bbb aaa\n"
result = self.fmt(
"Found 2 matches for old_string. Provide more context to make it unique, or use replace_all=True.",
0, "aaa", content,
)
assert result == ""
def test_silent_on_escape_drift_error(self):
"""Escape-drift errors are intentional blocks — hint would mislead."""
content = "x = 1\n"
result = self.fmt(
"Escape-drift detected: old_string and new_string contain the literal sequence '\\\\''...",
0, "x = \\'1\\'", content,
)
assert result == ""
def test_silent_on_identical_strings(self):
"""old_string == new_string — hint irrelevant."""
result = self.fmt(
"old_string and new_string are identical",
0, "foo", "foo bar\n",
)
assert result == ""
def test_silent_when_match_count_nonzero(self):
"""If match succeeded, we shouldn't be in the error path — defense in depth."""
result = self.fmt(
"Could not find a match for old_string in the file",
1, "foo", "foo bar\n",
)
assert result == ""
def test_silent_on_none_error(self):
"""No error at all — no hint."""
result = self.fmt(None, 0, "foo", "bar\n")
assert result == ""
def test_silent_when_no_similar_content(self):
"""Even for a valid no-match error, skip hint when nothing similar exists."""
result = self.fmt(
"Could not find a match for old_string in the file",
0, "totally_unique_xyzzy_qux", "abc\nxyz\n",
)
assert result == ""

View File

@@ -1,114 +0,0 @@
import json
import os
import textwrap
from pathlib import Path
import tools.skill_manager_tool as skill_manager_tool
from tools.file_tools import patch_tool
from tools.skill_manager_tool import _create_skill, _patch_skill
def _disable_patch_tool_guards(monkeypatch):
monkeypatch.setattr("tools.file_tools._check_sensitive_path", lambda _path: None)
monkeypatch.setattr("tools.file_tools._check_file_staleness", lambda _path, _task_id: None)
monkeypatch.setattr("tools.file_tools._log_and_check_conflict", lambda _path, _task_id, _action: None)
def test_patch_tool_replace_no_match_shows_rich_hint_without_legacy_hint(tmp_path, monkeypatch):
_disable_patch_tool_guards(monkeypatch)
sample = tmp_path / "sample.py"
sample.write_text("def foo():\n return 1\n\ndef bar():\n return 2\n", encoding="utf-8")
raw = patch_tool(
mode="replace",
path=str(sample),
old_string="def barycentric():",
new_string="def barycentric_new():",
task_id="qa960-replace-rich-hint",
)
result = json.loads(raw)
assert result["success"] is False
assert "Could not find a match" in result["error"]
assert "Did you mean one of these sections?" in result["error"]
assert "def bar():" in result["error"] or "def foo():" in result["error"]
assert "[Hint:" not in raw
def test_patch_tool_replace_ambiguous_error_does_not_show_did_you_mean(tmp_path, monkeypatch):
_disable_patch_tool_guards(monkeypatch)
sample = tmp_path / "sample.py"
sample.write_text("aaa\nbbb\naaa\n", encoding="utf-8")
raw = patch_tool(
mode="replace",
path=str(sample),
old_string="aaa",
new_string="ccc",
task_id="qa960-replace-ambiguous",
)
result = json.loads(raw)
assert result["success"] is False
assert "Found 2 matches" in result["error"]
assert "Did you mean one of these sections?" not in result["error"]
assert "[Hint:" not in raw
def test_patch_tool_v4a_no_match_shows_rich_hint(tmp_path, monkeypatch):
_disable_patch_tool_guards(monkeypatch)
sample = tmp_path / "sample.py"
sample.write_text("def foo():\n return 1\n", encoding="utf-8")
patch = textwrap.dedent(
f"""\
*** Begin Patch
*** Update File: {sample}
@@
-def barycentric():
+def barycentric_new():
*** End Patch
"""
)
raw = patch_tool(mode="patch", patch=patch, task_id="qa960-v4a-rich-hint")
result = json.loads(raw)
assert result["success"] is False
assert "Patch validation failed" in result["error"]
assert "Did you mean one of these sections?" in result["error"]
assert "def foo():" in result["error"]
def test_skill_patch_no_match_shows_rich_hint(tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
skills_dir = tmp_path / "skills"
skills_dir.mkdir(parents=True, exist_ok=True)
monkeypatch.setattr(skill_manager_tool, "SKILLS_DIR", skills_dir)
monkeypatch.setattr(skill_manager_tool, "_security_scan_skill", lambda _skill_dir: None)
_create_skill(
"qa-skill",
textwrap.dedent(
"""\
---
name: qa-skill
description: test
---
Step 1: Do the thing.
Step 2: Verify the thing.
"""
),
)
result = _patch_skill(
"qa-skill",
"Step 1: Do the production rollout.",
"Step 1: Updated.",
)
assert result["success"] is False
assert "Could not find a match" in result["error"]
assert "Did you mean one of these sections?" in result["error"]
assert "Step 1: Do the thing." in result["error"]
assert "file_preview" in result

View File

@@ -757,14 +757,12 @@ class ShellFileOperations(FileOperations):
content, old_string, new_string, replace_all
)
if error or match_count == 0:
err_msg = error or f"Could not find match for old_string in {path}"
try:
from tools.fuzzy_match import format_no_match_hint
err_msg += format_no_match_hint(err_msg, match_count, old_string, content)
except Exception:
pass
return PatchResult(error=err_msg)
if error:
return PatchResult(error=error)
if match_count == 0:
return PatchResult(error=f"Could not find match for old_string in {path}")
# Write back
write_result = self.write_file(path, new_content)
if write_result.error:

View File

@@ -8,7 +8,6 @@ import os
import threading
import time
from pathlib import Path
from typing import Any, Dict, Optional
from tools.binary_extensions import has_binary_extension
from tools.file_operations import ShellFileOperations
from agent.redact import redact_sensitive_text
@@ -691,11 +690,8 @@ def patch_tool(mode: str = "replace", path: str = None, old_string: str = None,
result_json = json.dumps(result_dict, ensure_ascii=False)
# Hint when old_string not found — saves iterations where the agent
# retries with stale content instead of re-reading the file.
# Suppressed when patch_replace already attached a rich "Did you mean?"
# snippet (which is strictly more useful than the generic hint).
if result_dict.get("error") and "Could not find" in str(result_dict["error"]):
if "Did you mean one of these sections?" not in str(result_dict["error"]):
result_json += "\n\n[Hint: old_string not found. Use read_file to verify the current content, or search_files to locate the text.]"
result_json += "\n\n[Hint: old_string not found. Use read_file to verify the current content, or search_files to locate the text.]"
return result_json
except Exception as e:
return tool_error(str(e))

View File

@@ -93,21 +93,6 @@ def fuzzy_find_and_replace(content: str, old_string: str, new_string: str,
f"Provide more context to make it unique, or use replace_all=True."
)
# Escape-drift guard: when the matched strategy is NOT `exact`,
# we matched via some form of normalization. If new_string
# contains shell/JSON-style escape sequences (\\' or \\") that
# would be written literally into the file but the matched
# region of the file has no such sequences, this is almost
# certainly tool-call serialization drift — the model typed
# an apostrophe/quote and the transport added a stray
# backslash. Writing new_string as-is would corrupt the file.
# Block with a helpful error so the model re-reads and retries
# instead of the caller silently persisting garbage (or not).
if strategy_name != "exact":
drift_err = _detect_escape_drift(content, matches, old_string, new_string)
if drift_err:
return content, 0, None, drift_err
# Perform replacement
new_content = _apply_replacements(content, matches, new_string)
return new_content, len(matches), strategy_name, None
@@ -116,46 +101,6 @@ def fuzzy_find_and_replace(content: str, old_string: str, new_string: str,
return content, 0, None, "Could not find a match for old_string in the file"
def _detect_escape_drift(content: str, matches: List[Tuple[int, int]],
old_string: str, new_string: str) -> Optional[str]:
"""Detect tool-call escape-drift artifacts in new_string.
Looks for ``\\'`` or ``\\"`` sequences that are present in both
old_string and new_string (i.e. the model copy-pasted them as "context"
it intended to preserve) but don't exist in the matched region of the
file. That pattern indicates the transport layer inserted spurious
shell-style escapes around apostrophes or quotes — writing new_string
verbatim would literally insert ``\\'`` into source code.
Returns an error string if drift is detected, None otherwise.
"""
# Cheap pre-check: bail out unless new_string actually contains a
# suspect escape sequence. This keeps the guard free for all the
# common, correct cases.
if "\\'" not in new_string and '\\"' not in new_string:
return None
# Aggregate matched regions of the file — that's what new_string will
# replace. If the suspect escapes are present there already, the
# model is genuinely preserving them (valid for some languages /
# escaped strings); accept the patch.
matched_regions = "".join(content[start:end] for start, end in matches)
for suspect in ("\\'", '\\"'):
if suspect in new_string and suspect in old_string and suspect not in matched_regions:
plain = suspect[1] # "'" or '"'
return (
f"Escape-drift detected: old_string and new_string contain "
f"the literal sequence {suspect!r} but the matched region of "
f"the file does not. This is almost always a tool-call "
f"serialization artifact where an apostrophe or quote got "
f"prefixed with a spurious backslash. Re-read the file with "
f"read_file and pass old_string/new_string without "
f"backslash-escaping {plain!r} characters."
)
return None
def _apply_replacements(content: str, matches: List[Tuple[int, int]], new_string: str) -> str:
"""
Apply replacements at the given positions.
@@ -619,86 +564,3 @@ def _map_normalized_positions(original: str, normalized: str,
original_matches.append((orig_start, min(orig_end, len(original))))
return original_matches
def find_closest_lines(old_string: str, content: str, context_lines: int = 2, max_results: int = 3) -> str:
"""Find lines in content most similar to old_string for "did you mean?" feedback.
Returns a formatted string showing the closest matching lines with context,
or empty string if no useful match is found.
"""
if not old_string or not content:
return ""
old_lines = old_string.splitlines()
content_lines = content.splitlines()
if not old_lines or not content_lines:
return ""
# Use first line of old_string as anchor for search
anchor = old_lines[0].strip()
if not anchor:
# Try second line if first is blank
candidates = [l.strip() for l in old_lines if l.strip()]
if not candidates:
return ""
anchor = candidates[0]
# Score each line in content by similarity to anchor
scored = []
for i, line in enumerate(content_lines):
stripped = line.strip()
if not stripped:
continue
ratio = SequenceMatcher(None, anchor, stripped).ratio()
if ratio > 0.3:
scored.append((ratio, i))
if not scored:
return ""
# Take top matches
scored.sort(key=lambda x: -x[0])
top = scored[:max_results]
parts = []
seen_ranges = set()
for _, line_idx in top:
start = max(0, line_idx - context_lines)
end = min(len(content_lines), line_idx + len(old_lines) + context_lines)
key = (start, end)
if key in seen_ranges:
continue
seen_ranges.add(key)
snippet = "\n".join(
f"{start + j + 1:4d}| {content_lines[start + j]}"
for j in range(end - start)
)
parts.append(snippet)
if not parts:
return ""
return "\n---\n".join(parts)
def format_no_match_hint(error: Optional[str], match_count: int,
old_string: str, content: str) -> str:
"""Return a '\\n\\nDid you mean...' snippet for plain no-match errors.
Gated so the hint only fires for actual "old_string not found" failures.
Ambiguous-match ("Found N matches"), escape-drift, and identical-strings
errors all have ``match_count == 0`` but a "did you mean?" snippet would
be misleading — those failed for unrelated reasons.
Returns an empty string when there's nothing useful to append.
"""
if match_count != 0:
return ""
if not error or not error.startswith("Could not find"):
return ""
hint = find_closest_lines(old_string, content)
if not hint:
return ""
return "\n\nDid you mean one of these sections?\n" + hint

View File

@@ -290,16 +290,10 @@ def _validate_operations(
)
if count == 0:
label = f"'{hunk.context_hint}'" if hunk.context_hint else "(no hint)"
msg = (
errors.append(
f"{op.file_path}: hunk {label} not found"
+ (f"{match_error}" if match_error else "")
)
try:
from tools.fuzzy_match import format_no_match_hint
msg += format_no_match_hint(match_error, count, search_pattern, simulated)
except Exception:
pass
errors.append(msg)
else:
# Advance simulation so subsequent hunks validate correctly.
# Reuse the result from the call above — no second fuzzy run.
@@ -543,13 +537,7 @@ def _apply_update(op: PatchOperation, file_ops: Any) -> Tuple[bool, str]:
error = None
if error:
err_msg = f"Could not apply hunk: {error}"
try:
from tools.fuzzy_match import format_no_match_hint
err_msg += format_no_match_hint(error, 0, search_pattern, new_content)
except Exception:
pass
return False, err_msg
return False, f"Could not apply hunk: {error}"
else:
# Addition-only hunk (no context or removed lines).
# Insert at the location indicated by the context hint, or at end of file.

View File

@@ -575,15 +575,9 @@ def _patch_skill(
if match_error:
# Show a short preview of the file so the model can self-correct
preview = content[:500] + ("..." if len(content) > 500 else "")
err_msg = match_error
try:
from tools.fuzzy_match import format_no_match_hint
err_msg += format_no_match_hint(match_error, match_count, old_string, content)
except Exception:
pass
return {
"success": False,
"error": err_msg,
"error": match_error,
"file_preview": preview,
}