ewilliams28/turnstone
1
0
Fork 0
mirror of https://github.com/turnstonelabs/turnstone.git synced 2026-08-12 23:12:23 -06:00
Code Issues Packages Projects Releases Wiki Activity

test(golden): freeze the anthropic-compatible reasoning-effort wire

Browse Source 
The wire-payload golden matrix had no anthropic-compatible coverage —
both AnthropicProvider rows are the native lane (compat=False), so the
distinct compat wire shape (reasoning control in
extra_body.chat_template_kwargs, never the native thinking param) was
unfrozen. Add the compat lane across all eight representative fixtures
with a manual-mode capability (the lane has no static table, so caps
ride in as a model definition would supply them) and reasoning_effort=
high: every golden now pins {enable_thinking: true, reasoning_effort:
high} in chat_template_kwargs, asserts the native thinking param is
absent, and preserves temperature (no forced 1.0). _capture gains an
optional caps override to support the no-static-table lane.
This commit is contained in:
Patrick Buckley
2026-07-05 01:59:14 -07:00
parent 9c90fe2722
commit 6f8efaa44e
9 changed files with 523 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/data/wire_payloads/anthropic_compat__mid_orphan.json
+78
View File
@@ -0,0 +1,78 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Weather in Paris and London?",
"role": "user"
},
{
"content": [
{
"id": "call_1",
"input": {
"city": "Paris"
},
"name": "get_weather",
"type": "tool_use"
},
{
"id": "call_2",
"input": {
"city": "London"
},
"name": "get_weather",
"type": "tool_use"
}
],
"role": "assistant"
},
{
"content": [
{
"content": "18C, clear.",
"tool_use_id": "call_1",
"type": "tool_result"
},
{
"content": "Tool execution was cancelled. Outcome UNKNOWN — this call may have begun executing before the generation was stopped; do not assume it did not run, and reconcile before re-issuing it.",
"is_error": true,
"tool_use_id": "call_2",
"type": "tool_result"
},
{
"text": "Actually, never mind London.",
"type": "text"
}
],
"role": "user"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5,
"tools": [
{
"description": "Look up the weather for a city.",
"input_schema": {
"properties": {
"city": {
"type": "string"
}
},
"required": [
"city"
],
"type": "object"
},
"name": "get_weather"
}
]
}
tests/data/wire_payloads/anthropic_compat__multipart.json
+33
View File
@@ -0,0 +1,33 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": [
{
"text": "What's in this image?",
"type": "text"
},
{
"source": {
"data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==",
"media_type": "image/png",
"type": "base64"
},
"type": "image"
}
],
"role": "user"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5
}
tests/data/wire_payloads/anthropic_compat__native_orphan.json
+70
View File
@@ -0,0 +1,70 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Think about the weather.",
"role": "user"
},
{
"content": [
{
"signature": "sig-abc",
"thinking": "The user wants weather.",
"type": "thinking"
},
{
"text": "Let me check.",
"type": "text"
},
{
"id": "call_1",
"input": {
"city": "Paris"
},
"name": "get_weather",
"type": "tool_use"
}
],
"role": "assistant"
},
{
"content": [
{
"content": "Tool execution was cancelled. Outcome UNKNOWN — this call may have begun executing before the generation was stopped; do not assume it did not run, and reconcile before re-issuing it.",
"is_error": true,
"tool_use_id": "call_1",
"type": "tool_result"
}
],
"role": "user"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5,
"tools": [
{
"description": "Look up the weather for a city.",
"input_schema": {
"properties": {
"city": {
"type": "string"
}
},
"required": [
"city"
],
"type": "object"
},
"name": "get_weather"
}
]
}
tests/data/wire_payloads/anthropic_compat__native_reasoning.json
+69
View File
@@ -0,0 +1,69 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Think about the weather.",
"role": "user"
},
{
"content": [
{
"signature": "sig-abc",
"thinking": "The user wants weather.",
"type": "thinking"
},
{
"text": "Let me check.",
"type": "text"
},
{
"id": "call_1",
"input": {
"city": "Paris"
},
"name": "get_weather",
"type": "tool_use"
}
],
"role": "assistant"
},
{
"content": [
{
"content": "18C, clear.",
"tool_use_id": "call_1",
"type": "tool_result"
}
],
"role": "user"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5,
"tools": [
{
"description": "Look up the weather for a city.",
"input_schema": {
"properties": {
"city": {
"type": "string"
}
},
"required": [
"city"
],
"type": "object"
},
"name": "get_weather"
}
]
}
tests/data/wire_payloads/anthropic_compat__operator_system.json
+63
View File
@@ -0,0 +1,63 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Run the deploy.",
"role": "user"
},
{
"content": [
{
"id": "call_1",
"input": {},
"name": "deploy",
"type": "tool_use"
}
],
"role": "assistant"
},
{
"content": [
{
"content": "deployed",
"tool_use_id": "call_1",
"type": "tool_result"
},
{
"text": "Great, what's next?",
"type": "text"
}
],
"role": "user"
}
],
"model": "qwen3.6-27b",
"system": "Output-guard: deploy output looked clean.",
"temperature": 0.5,
"tools": [
{
"description": "Look up the weather for a city.",
"input_schema": {
"properties": {
"city": {
"type": "string"
}
},
"required": [
"city"
],
"type": "object"
},
"name": "get_weather"
}
]
}
tests/data/wire_payloads/anthropic_compat__text.json
+33
View File
@@ -0,0 +1,33 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Hi there.",
"role": "user"
},
{
"content": [
{
"text": "Hello! How can I help?",
"type": "text"
}
],
"role": "assistant"
},
{
"content": "What's the weather in Paris?",
"role": "user"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5
}
tests/data/wire_payloads/anthropic_compat__toolcall_complete.json
+69
View File
@@ -0,0 +1,69 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Weather in Paris?",
"role": "user"
},
{
"content": [
{
"id": "call_1",
"input": {
"city": "Paris"
},
"name": "get_weather",
"type": "tool_use"
}
],
"role": "assistant"
},
{
"content": [
{
"content": "18C, clear.",
"tool_use_id": "call_1",
"type": "tool_result"
}
],
"role": "user"
},
{
"content": [
{
"text": "It's 18C and clear in Paris.",
"type": "text"
}
],
"role": "assistant"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5,
"tools": [
{
"description": "Look up the weather for a city.",
"input_schema": {
"properties": {
"city": {
"type": "string"
}
},
"required": [
"city"
],
"type": "object"
},
"name": "get_weather"
}
]
}
tests/data/wire_payloads/anthropic_compat__trailing_orphan.json
+61
View File
@@ -0,0 +1,61 @@
{
"cache_control": {
"type": "ephemeral"
},
"extra_body": {
"chat_template_kwargs": {
"enable_thinking": true,
"reasoning_effort": "high"
}
},
"max_tokens": 4096,
"messages": [
{
"content": "Weather in Paris?",
"role": "user"
},
{
"content": [
{
"id": "call_1",
"input": {
"city": "Paris"
},
"name": "get_weather",
"type": "tool_use"
}
],
"role": "assistant"
},
{
"content": [
{
"content": "Tool execution was cancelled. Outcome UNKNOWN — this call may have begun executing before the generation was stopped; do not assume it did not run, and reconcile before re-issuing it.",
"is_error": true,
"tool_use_id": "call_1",
"type": "tool_result"
}
],
"role": "user"
}
],
"model": "qwen3.6-27b",
"temperature": 0.5,
"tools": [
{
"description": "Look up the weather for a city.",
"input_schema": {
"properties": {
"city": {
"type": "string"
}
},
"required": [
"city"
],
"type": "object"
},
"name": "get_weather"
}
]
}
tests/test_wire_payload_golden.py
+47 -3
View File
@@ -36,6 +36,7 @@ from turnstone.core.providers._anthropic import AnthropicProvider
from turnstone.core.providers._google import GoogleProvider
from turnstone.core.providers._openai_chat import OpenAIChatCompletionsProvider
from turnstone.core.providers._openai_responses import OpenAIResponsesProvider
from turnstone.core.providers._protocol import ModelCapabilities
if TYPE_CHECKING:
from turnstone.core.providers._protocol import LLMProvider
@@ -45,11 +46,21 @@ _UPDATE = os.environ.get("UPDATE_WIRE_GOLDENS") == "1"
def _capture(
provider: LLMProvider, *, model: str, messages: list[dict[str, Any]], **opts: Any
provider: LLMProvider,
*,
model: str,
messages: list[dict[str, Any]],
caps: ModelCapabilities | None = None,
**opts: Any,
) -> dict[str, Any]:
"""Drive ``create_streaming`` against a recording client; return the SDK kwargs."""
"""Drive ``create_streaming`` against a recording client; return the SDK kwargs.
*caps* overrides the provider's own capability lookup — required for the
anthropic-compatible lane, which has no static table (an operator-run model
definition supplies its capabilities).
"""
client = RecordingClient()
caps = provider.get_capabilities(model)
caps = caps or provider.get_capabilities(model)
# Mirror the session's wire prep: orphan repair runs once on the canonical
# Turns (``ChatSession._prepare_wire_messages``), then the result is lowered
# to the dict projection the translator consumes. Fixtures arrive
@@ -264,3 +275,36 @@ def test_wire_payload(
provider = factory()
payload = _capture(provider, model=model, messages=[dict(m) for m in messages], **opts)
_assert_golden(f"{provider_id}__{fixture_id}", payload)
# The anthropic-compatible lane (vLLM /v1/messages) has no static capability
# table and carries reasoning control in ``extra_body.chat_template_kwargs``
# rather than the native ``thinking`` param — a wire shape the matrix above
# never exercises (both AnthropicProvider rows are the native lane). Freeze it
# with the capabilities a manual-mode model definition supplies and a real
# effort level, so the graded ``reasoning_effort`` key is pinned in the golden
# (never the native ``thinking`` param, and no forced ``temperature=1.0``).
_COMPAT_CAPS = ModelCapabilities(
context_window=262144,
max_output_tokens=64000,
token_param="max_tokens",
thinking_mode="manual",
thinking_param="enable_thinking",
supports_reasoning_replay=True,
)
@pytest.mark.parametrize("fixture_id", sorted(_FIXTURES))
def test_wire_payload_anthropic_compat(fixture_id: str) -> None:
messages, opts = _FIXTURES[fixture_id]
provider = AnthropicProvider(compat=True)
payload = _capture(
provider,
model="qwen3.6-27b",
messages=[dict(m) for m in messages],
caps=_COMPAT_CAPS,
reasoning_effort="high",
**opts,
)
assert "thinking" not in payload, "compat lane must never send the native thinking param"
_assert_golden(f"anthropic_compat__{fixture_id}", payload)