feat(anthropic): update model YAMLs [bot] - #2087
Open
models-bot[bot] wants to merge 1 commit into
Open
Conversation
Contributor
|
/test-models |
Collaborator
Gateway test results
Failures (36)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
],
tools=tools,
tool_choice="auto",
stream=False,
)
_message = response.choices[0].message
if _message.tool_calls:
for _tc in _message.tool_calls:
print(f"Function: {_tc.function.name}")
print(f"Arguments: {_tc.function.arguments}")
else:
print(_message.content)
if not _message.tool_calls or len(_message.tool_calls) == 0:
raise Exception("VALIDATION FAILED: tool-call - no tool calls in response")
print("VALIDATION: tool-call SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
],
tools=tools,
tool_choice="auto",
stream=True,
)
_tool_calls_made = False
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if delta.tool_calls:
_tool_calls_made = True
for _tc in delta.tool_calls:
if _tc.function:
print(_tc.function.arguments or "", end="", flush=True)
if not _tool_calls_made:
raise Exception("VALIDATION FAILED: tool-call stream - no tool calls received")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
],
tools=tools,
tool_choice="auto",
parallel_tool_calls=True,
stream=False,
)
_message = response.choices[0].message
if _message.tool_calls:
print(f"Number of parallel tool calls: {len(_message.tool_calls)}")
for _tc in _message.tool_calls:
print(f"Function: {_tc.function.name}")
print(f"Arguments: {_tc.function.arguments}")
else:
print(_message.content)
if not _message.tool_calls or len(_message.tool_calls) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call - expected at least 1 tool call, "
f"got {len(_message.tool_calls) if _message.tool_calls else 0}"
)
print("VALIDATION: parallel-tool-call SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
],
max_tokens=1000,
stream=False,
)
print(response.choices[0].message.content)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning_effort="medium",
stream=True,
)
_reasoning_detected = False
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if getattr(delta, "reasoning_content", None) is not None:
_reasoning_detected = True
if getattr(delta, "reasoning", None) is not None:
_reasoning_detected = True
_usage = getattr(chunk, "usage", None)
if _usage is not None:
_details = getattr(_usage, "completion_tokens_details", None)
if _details and getattr(_details, "reasoning_tokens", 0) > 0:
_reasoning_detected = True
if not _reasoning_detected:
raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
print("\nVALIDATION: reasoning stream SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if not _tool_uses:
raise Exception("VALIDATION FAILED: tool-call stream - no tool uses in Anthropic stream response")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
)
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if not _tool_uses:
raise Exception("VALIDATION FAILED: tool-call - no tool uses in Anthropic response")
print("VALIDATION: tool-call SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant.",
messages=messages,
max_tokens=1000,
)
for block in response.content:
if block.type == "text":
print(block.text)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
],
tools=tools,
tool_choice="auto",
parallel_tool_calls=True,
stream=True,
)
_tool_call_indices = set()
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if delta.tool_calls:
for _tc in delta.tool_calls:
_tool_call_indices.add(_tc.index)
if _tc.function:
print(_tc.function.arguments or "", end="", flush=True)
if len(_tool_call_indices) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call stream - expected at least 1 tool call, "
f"got {len(_tool_call_indices)}"
)
print(f"\nNumber of parallel tool calls: {len(_tool_call_indices)}")
print("VALIDATION: parallel-tool-call stream SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps.",
messages=messages,
max_tokens=16000,
thinking={"type":"adaptive"},
)
for block in response.content:
if block.type == "thinking":
print(f"Thinking: {block.thinking[:200]}...")
elif block.type == "text":
print(block.text)
_reasoning_detected = False
for block in response.content:
if block.type == "thinking":
_reasoning_detected = True
if hasattr(response, "usage") and response.usage:
if getattr(response.usage, "cache_creation_input_tokens", 0) or getattr(response.usage, "cache_read_input_tokens", 0):
pass
if not _reasoning_detected:
print("Response content types: ", [block.type for block in response.content])
raise Exception("VALIDATION FAILED: reasoning - no thinking blocks in Anthropic response")
print("VALIDATION: reasoning SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
],
max_tokens=1000,
stream=True,
)
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-4-8",
messages=[
{"role": "system", "content": "You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning_effort="medium",
stream=False,
)
_usage = getattr(response, "usage", None)
_reasoning_detected = False
_choices = getattr(response, "choices", None)
if _choices and len(_choices) > 0:
_message = getattr(_choices[0], "message", None)
else:
_message = None
if _message and getattr(_message, "content", None) is not None:
print(_message.content)
if _usage is not None:
_output_token_details = getattr(_usage, "completion_tokens_details", None)
if _output_token_details and getattr(_output_token_details, "reasoning_tokens", 0) > 0:
_reasoning_detected = True
elif getattr(_usage, "reasoning", None) is not None:
_reasoning_detected = True
if getattr(_message, "reasoning_content", None) is not None:
_reasoning_detected = True
elif getattr(_message, "reasoning", None) is not None:
_reasoning_detected = True
if not _reasoning_detected:
print("Response: ", response)
raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
print("VALIDATION: reasoning SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
)
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if _tool_uses:
print(f"Number of parallel tool calls: {len(_tool_uses)}")
if not _tool_uses or len(_tool_uses) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call - expected at least 1 tool call, "
f"got {len(_tool_uses) if _tool_uses else 0}"
)
print("VALIDATION: parallel-tool-call SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if _tool_uses:
print(f"Number of parallel tool calls: {len(_tool_uses)}")
if not _tool_uses or len(_tool_uses) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call stream - expected at least 1 tool call, "
f"got {len(_tool_uses) if _tool_uses else 0}"
)
print(f"\nVALIDATION: parallel-tool-call stream SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant.",
messages=messages,
max_tokens=1000,
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-4-8"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps.",
messages=messages,
max_tokens=16000,
thinking={"type":"adaptive"},
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "thinking":
print(f"Thinking: {block.thinking[:200]}...")
elif block.type == "text":
print(block.text)
_reasoning_detected = False
for block in response.content:
if block.type == "thinking":
_reasoning_detected = True
if not _reasoning_detected:
print("Response content types: ", [block.type for block in response.content])
raise Exception("VALIDATION FAILED: reasoning stream - no thinking blocks in Anthropic stream response")
print("\nVALIDATION: reasoning stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
],
tools=tools,
tool_choice="auto",
stream=True,
)
_tool_calls_made = False
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if delta.tool_calls:
_tool_calls_made = True
for _tc in delta.tool_calls:
if _tc.function:
print(_tc.function.arguments or "", end="", flush=True)
if not _tool_calls_made:
raise Exception("VALIDATION FAILED: tool-call stream - no tool calls received")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
import json
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response_schema = json.loads('''{
"title": "CalendarEvent",
"type": "object",
"properties": {
"name": { "type": "string" },
"date": { "type": "string" },
"participants": {
"type": "array",
"items": { "type": "string" }
}
},
"required": ["name", "date", "participants"],
"additionalProperties": false
}''')
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "Extract the event information as JSON."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
response_format={"type": "json_schema", "json_schema": {"name": "CalendarEvent", "schema": response_schema}},
stream=True,
)
import json as _json
_accumulated = ""
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
_accumulated += delta.content
print(delta.content, end="", flush=True)
if not _accumulated:
raise Exception("VALIDATION FAILED: structured-output stream - no content received")
_parsed = _json.loads(_accumulated)
if "name" not in _parsed or "date" not in _parsed or "participants" not in _parsed:
raise Exception("VALIDATION FAILED: structured-output stream - missing expected fields (name, date, participants)")
if not isinstance(_parsed.get("participants"), list):
raise Exception("VALIDATION FAILED: structured-output stream - 'participants' is not a list, schema not enforced")
if set(_parsed.keys()) != {"name", "date", "participants"}:
raise Exception(
f"VALIDATION FAILED: structured-output stream - unexpected keys present: {set(_parsed.keys())}"
)
print("\nVALIDATION: structured-output stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning_effort="medium",
stream=True,
)
_reasoning_detected = False
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if getattr(delta, "reasoning_content", None) is not None:
_reasoning_detected = True
if getattr(delta, "reasoning", None) is not None:
_reasoning_detected = True
_usage = getattr(chunk, "usage", None)
if _usage is not None:
_details = getattr(_usage, "completion_tokens_details", None)
if _details and getattr(_details, "reasoning_tokens", 0) > 0:
_reasoning_detected = True
if not _reasoning_detected:
raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
print("\nVALIDATION: reasoning stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
],
max_tokens=256,
stream=False,
)
print(response.choices[0].message.content)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
],
tools=tools,
tool_choice="auto",
parallel_tool_calls=True,
stream=False,
)
_message = response.choices[0].message
if _message.tool_calls:
print(f"Number of parallel tool calls: {len(_message.tool_calls)}")
for _tc in _message.tool_calls:
print(f"Function: {_tc.function.name}")
print(f"Arguments: {_tc.function.arguments}")
else:
print(_message.content)
if not _message.tool_calls or len(_message.tool_calls) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call - expected at least 1 tool call, "
f"got {len(_message.tool_calls) if _message.tool_calls else 0}"
)
print("VALIDATION: parallel-tool-call SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
],
tools=tools,
tool_choice="auto",
parallel_tool_calls=True,
stream=True,
)
_tool_call_indices = set()
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if delta.tool_calls:
for _tc in delta.tool_calls:
_tool_call_indices.add(_tc.index)
if _tc.function:
print(_tc.function.arguments or "", end="", flush=True)
if len(_tool_call_indices) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call stream - expected at least 1 tool call, "
f"got {len(_tool_call_indices)}"
)
print(f"\nNumber of parallel tool calls: {len(_tool_call_indices)}")
print("VALIDATION: parallel-tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
],
tools=tools,
tool_choice="auto",
stream=False,
)
_message = response.choices[0].message
if _message.tool_calls:
for _tc in _message.tool_calls:
print(f"Function: {_tc.function.name}")
print(f"Arguments: {_tc.function.arguments}")
else:
print(_message.content)
if not _message.tool_calls or len(_message.tool_calls) == 0:
raise Exception("VALIDATION FAILED: tool-call - no tool calls in response")
print("VALIDATION: tool-call SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
)
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if not _tool_uses:
raise Exception("VALIDATION FAILED: tool-call - no tool uses in Anthropic response")
print("VALIDATION: tool-call SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
],
max_tokens=256,
stream=True,
)
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if not _tool_uses:
raise Exception("VALIDATION FAILED: tool-call stream - no tool uses in Anthropic stream response")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetimport anthropic
import json
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
response_schema = {
"type": "object",
"properties": {
"name": {"type": "string"},
"date": {"type": "string"},
"participants": {
"type": "array",
"items": {"type": "string"},
},
},
"required": ["name", "date", "participants"],
}
tools = [
{
"name": "CalendarEvent",
"description": "Extract event information as a structured CalendarEvent.",
"input_schema": response_schema,
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
]
with client.messages.stream(
model=_model,
system="Extract the event information using the CalendarEvent tool.",
messages=messages,
tools=tools,
tool_choice={"type": "tool", "name": "CalendarEvent"},
max_tokens=1024,
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "tool_use":
print(json.dumps(block.input, indent=2))
elif block.type == "text":
print(block.text)
import json as _json
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if _tool_uses:
_parsed = _tool_uses[0].input
else:
_text_blocks = [block.text for block in response.content if block.type == "text"]
_text = "".join(_text_blocks)
if not _text:
raise Exception("VALIDATION FAILED: structured-output stream - no content received from Anthropic stream")
_parsed = _json.loads(_text)
if "name" not in _parsed or "date" not in _parsed or "participants" not in _parsed:
raise Exception("VALIDATION FAILED: structured-output stream - missing expected fields (name, date, participants)")
if not isinstance(_parsed.get("participants"), list):
raise Exception("VALIDATION FAILED: structured-output stream - 'participants' is not a list, schema not enforced")
print("\nVALIDATION: structured-output stream SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
)
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if _tool_uses:
print(f"Number of parallel tool calls: {len(_tool_uses)}")
if not _tool_uses or len(_tool_uses) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call - expected at least 1 tool call, "
f"got {len(_tool_uses) if _tool_uses else 0}"
)
print("VALIDATION: parallel-tool-call SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps.",
messages=messages,
max_tokens=16000,
thinking={"type":"adaptive"},
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "thinking":
print(f"Thinking: {block.thinking[:200]}...")
elif block.type == "text":
print(block.text)
_reasoning_detected = False
for block in response.content:
if block.type == "thinking":
_reasoning_detected = True
if not _reasoning_detected:
print("Response content types: ", [block.type for block in response.content])
raise Exception("VALIDATION FAILED: reasoning stream - no thinking blocks in Anthropic stream response")
print("\nVALIDATION: reasoning stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
import json
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response_schema = json.loads('''{
"title": "CalendarEvent",
"type": "object",
"properties": {
"name": { "type": "string" },
"date": { "type": "string" },
"participants": {
"type": "array",
"items": { "type": "string" }
}
},
"required": ["name", "date", "participants"],
"additionalProperties": false
}''')
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "Extract the event information as JSON."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
response_format={"type": "json_schema", "json_schema": {"name": "CalendarEvent", "schema": response_schema}},
stream=False,
)
import json as _json
_content = response.choices[0].message.content
print(_content)
if not _content:
raise Exception("VALIDATION FAILED: structured-output - response content is empty")
_parsed = _json.loads(_content)
if "name" not in _parsed or "date" not in _parsed or "participants" not in _parsed:
raise Exception("VALIDATION FAILED: structured-output - missing expected fields (name, date, participants)")
if not isinstance(_parsed.get("participants"), list):
raise Exception("VALIDATION FAILED: structured-output - 'participants' is not a list, schema not enforced")
if set(_parsed.keys()) != {"name", "date", "participants"}:
raise Exception(
f"VALIDATION FAILED: structured-output - unexpected keys present: {set(_parsed.keys())}"
)
print("VALIDATION: structured-output SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant.",
messages=messages,
max_tokens=256,
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location.",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
},
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London and Paris. You MUST make both tool calls strictly in parallel, not sequentially."},
]
with client.messages.stream(
model=_model,
system="You are a helpful assistant with access to tools. You MUST strictly call multiple tools in parallel whenever possible. Never call them sequentially.",
messages=messages,
tools=tools,
tool_choice={"type": "auto"},
max_tokens=1024,
) as stream:
response = stream.get_final_message()
for block in response.content:
if block.type == "tool_use":
print(f"Tool: {block.name}")
print(f"Input: {block.input}")
elif block.type == "text":
print(block.text)
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if _tool_uses:
print(f"Number of parallel tool calls: {len(_tool_uses)}")
if not _tool_uses or len(_tool_uses) < 1:
raise Exception(
f"VALIDATION FAILED: parallel-tool-call stream - expected at least 1 tool call, "
f"got {len(_tool_uses) if _tool_uses else 0}"
)
print(f"\nVALIDATION: parallel-tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-anthropic/claude-opus-5",
messages=[
{"role": "system", "content": "You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning_effort="medium",
stream=False,
)
_usage = getattr(response, "usage", None)
_reasoning_detected = False
_choices = getattr(response, "choices", None)
if _choices and len(_choices) > 0:
_message = getattr(_choices[0], "message", None)
else:
_message = None
if _message and getattr(_message, "content", None) is not None:
print(_message.content)
if _usage is not None:
_output_token_details = getattr(_usage, "completion_tokens_details", None)
if _output_token_details and getattr(_output_token_details, "reasoning_tokens", 0) > 0:
_reasoning_detected = True
elif getattr(_usage, "reasoning", None) is not None:
_reasoning_detected = True
if getattr(_message, "reasoning_content", None) is not None:
_reasoning_detected = True
elif getattr(_message, "reasoning", None) is not None:
_reasoning_detected = True
if not _reasoning_detected:
print("Response: ", response)
raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
print("VALIDATION: reasoning SUCCESS")
ErrorCode snippetimport anthropic
import json
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
response_schema = {
"type": "object",
"properties": {
"name": {"type": "string"},
"date": {"type": "string"},
"participants": {
"type": "array",
"items": {"type": "string"},
},
},
"required": ["name", "date", "participants"],
}
tools = [
{
"name": "CalendarEvent",
"description": "Extract event information as a structured CalendarEvent.",
"input_schema": response_schema,
},
]
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
]
response = client.messages.create(
model=_model,
system="Extract the event information using the CalendarEvent tool.",
messages=messages,
tools=tools,
tool_choice={"type": "tool", "name": "CalendarEvent"},
max_tokens=1024,
)
for block in response.content:
if block.type == "tool_use":
print(json.dumps(block.input, indent=2))
elif block.type == "text":
print(block.text)
import json as _json
_tool_uses = [block for block in response.content if block.type == "tool_use"]
if _tool_uses:
_parsed = _tool_uses[0].input
else:
_text_blocks = [block.text for block in response.content if block.type == "text"]
_text = "".join(_text_blocks)
if not _text:
raise Exception("VALIDATION FAILED: structured-output - no content received from Anthropic response")
_parsed = _json.loads(_text)
if "name" not in _parsed or "date" not in _parsed or "participants" not in _parsed:
raise Exception("VALIDATION FAILED: structured-output - missing expected fields (name, date, participants)")
if not isinstance(_parsed.get("participants"), list):
raise Exception("VALIDATION FAILED: structured-output - 'participants' is not a list, schema not enforced")
print("VALIDATION: structured-output SUCCESS")
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant.",
messages=messages,
max_tokens=256,
)
for block in response.content:
if block.type == "text":
print(block.text)
ErrorCode snippetimport anthropic
_api_key = "***"
_model = "test-v2-anthropic/claude-opus-5"
client = anthropic.Anthropic(
api_key=_api_key,
base_url="https://internal.devtest.truefoundry.tech/api/llm",
)
messages = [
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
]
response = client.messages.create(
model=_model,
system="You are a helpful assistant. You MUST think step by step and show your reasoning. Never skip reasoning steps.",
messages=messages,
max_tokens=16000,
thinking={"type":"adaptive"},
)
for block in response.content:
if block.type == "thinking":
print(f"Thinking: {block.thinking[:200]}...")
elif block.type == "text":
print(block.text)
_reasoning_detected = False
for block in response.content:
if block.type == "thinking":
_reasoning_detected = True
if hasattr(response, "usage") and response.usage:
if getattr(response.usage, "cache_creation_input_tokens", 0) or getattr(response.usage, "cache_read_input_tokens", 0):
pass
if not _reasoning_detected:
print("Response content types: ", [block.type for block in response.content])
raise Exception("VALIDATION FAILED: reasoning - no thinking blocks in Anthropic response")
print("VALIDATION: reasoning SUCCESS") |
Archit-Kumar-16
approved these changes
Aug 9, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Auto-generated by poc-agent for provider
anthropic.Note
Low Risk
Metadata-only YAML updates with no runtime or routing logic changes.
Overview
Adds
retirementDatemetadata to two Anthropic model definitions so consumers can plan around end-of-life.claude-opus-4-8.yamlis set to retire on 2027-05-28;claude-opus-5.yamlon 2027-07-24. No pricing, limits, features, or status fields are changed.Reviewed by Cursor Bugbot for commit ace3343. Bugbot is set up for automated code reviews on this repo. Configure here.