feat(aws-bedrock-mantle): update model YAMLs [bot] - #2115
Closed
models-bot[bot] wants to merge 2 commits into
Closed
feat(aws-bedrock-mantle): update model YAMLs [bot]#2115models-bot[bot] wants to merge 2 commits into
models-bot[bot] wants to merge 2 commits into
Conversation
Contributor
|
/test-models |
Collaborator
Gateway test results
Failures (32)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"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,
)
_tool_calls = [_item for _item in response.output if _item.type == "function_call"]
if not _tool_calls:
print(response.output_text)
print(f"Tools sent: {len(response.tools)}, tool_choice: {response.tool_choice}")
raise Exception(
"VALIDATION FAILED: tool-call - no tool calls in response"
)
for _tc in _tool_calls:
print(f"Function: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("VALIDATION: tool-call 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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
text={"format": {"type": "json_schema", "name": "CalendarEvent", "strict": True, "schema": response_schema}},
stream=True,
)
import json as _json
_accumulated = ""
for event in response:
if event.type == "response.output_text.delta":
_accumulated += event.delta
print(event.delta, 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")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"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,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: tool-call stream - no completed response received"
)
_tool_calls = [_item for _item in _completed_response.output if _item.type == "function_call"]
if not _tool_calls:
print(_completed_response.output_text)
print(f"Tools sent: {len(_completed_response.tools)}, tool_choice: {_completed_response.tool_choice}")
raise Exception(
"VALIDATION FAILED: tool-call stream - no tool calls in response"
)
for _tc in _tool_calls:
print(f"\nFunction: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"role": "user", "content": "What is the capital of France?"},
],
stream=True,
)
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"role": "user", "content": "What is the capital of France?"},
],
stream=False,
)
print(response.output_text)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning={"effort": "medium"},
stream=False,
)
_reasoning_items = [
_item for _item in (getattr(response, "output", None) or [])
if getattr(_item, "type", None) == "reasoning"
]
_usage = getattr(response, "usage", None)
_details = getattr(_usage, "output_tokens_details", None) if _usage else None
_reasoning_tokens = getattr(_details, "reasoning_tokens", 0) if _details else 0
if response.output_text:
print(response.output_text)
if not _reasoning_items and not _reasoning_tokens:
raise Exception(
"VALIDATION FAILED: reasoning - no reasoning output items or reasoning tokens in response"
)
print("VALIDATION: reasoning 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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
text={"format": {"type": "json_schema", "name": "CalendarEvent", "strict": True, "schema": response_schema}},
stream=False,
)
import json as _json
_content = response.output_text
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 snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-sol",
input=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning={"effort": "medium"},
stream=True,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: reasoning stream - no completed response received"
)
_reasoning_items = [
_item for _item in (getattr(_completed_response, "output", None) or [])
if getattr(_item, "type", None) == "reasoning"
]
_usage = getattr(_completed_response, "usage", None)
_details = getattr(_usage, "output_tokens_details", None) if _usage else None
_reasoning_tokens = getattr(_details, "reasoning_tokens", 0) if _details else 0
if not _reasoning_items and not _reasoning_tokens:
raise Exception(
"VALIDATION FAILED: reasoning stream - no reasoning output items or reasoning tokens in 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",
"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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"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,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: tool-call stream - no completed response received"
)
_tool_calls = [_item for _item in _completed_response.output if _item.type == "function_call"]
if not _tool_calls:
print(_completed_response.output_text)
print(f"Tools sent: {len(_completed_response.tools)}, tool_choice: {_completed_response.tool_choice}")
raise Exception(
"VALIDATION FAILED: tool-call stream - no tool calls in response"
)
for _tc in _tool_calls:
print(f"\nFunction: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
text={"format": {"type": "json_object"}},
stream=False,
)
import json as _json
_content = response.output_text
print(_content)
if not _content:
raise Exception("VALIDATION FAILED: json-output - response content is empty")
_json.loads(_content)
print("VALIDATION: json-output SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning={"effort": "medium"},
stream=False,
)
_reasoning_items = [
_item for _item in (getattr(response, "output", None) or [])
if getattr(_item, "type", None) == "reasoning"
]
_usage = getattr(response, "usage", None)
_details = getattr(_usage, "output_tokens_details", None) if _usage else None
_reasoning_tokens = getattr(_details, "reasoning_tokens", 0) if _details else 0
if response.output_text:
print(response.output_text)
if not _reasoning_items and not _reasoning_tokens:
raise Exception(
"VALIDATION FAILED: reasoning - no reasoning output items or reasoning tokens in 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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "What is the capital of France?"},
],
stream=True,
)
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"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,
)
_tool_calls = [_item for _item in response.output if _item.type == "function_call"]
if len(_tool_calls) < 1:
print(response.output_text)
print(f"Tools sent: {len(response.tools)}, tool_choice: {response.tool_choice}")
raise Exception(
f"VALIDATION FAILED: parallel-tool-call - expected at least 1 tool call, "
f"got {len(_tool_calls)}"
)
for _tc in _tool_calls:
print(f"Function: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
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",
"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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"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,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: parallel-tool-call stream - no completed response received"
)
_tool_calls = [_item for _item in _completed_response.output if _item.type == "function_call"]
if len(_tool_calls) < 1:
print(_completed_response.output_text)
print(f"Tools sent: {len(_completed_response.tools)}, tool_choice: {_completed_response.tool_choice}")
raise Exception(
f"VALIDATION FAILED: parallel-tool-call stream - expected at least 1 tool call, "
f"got {len(_tool_calls)}"
)
for _tc in _tool_calls:
print(f"\nFunction: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("\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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
text={"format": {"type": "json_object"}},
stream=True,
)
import json as _json
_accumulated = ""
for event in response:
if event.type == "response.output_text.delta":
_accumulated += event.delta
print(event.delta, end="", flush=True)
if not _accumulated:
raise Exception("VALIDATION FAILED: json-output stream - no content received")
_json.loads(_accumulated)
print("\nVALIDATION: json-output stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning={"effort": "medium"},
stream=True,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: reasoning stream - no completed response received"
)
_reasoning_items = [
_item for _item in (getattr(_completed_response, "output", None) or [])
if getattr(_item, "type", None) == "reasoning"
]
_usage = getattr(_completed_response, "usage", None)
_details = getattr(_usage, "output_tokens_details", None) if _usage else None
_reasoning_tokens = getattr(_details, "reasoning_tokens", 0) if _details else 0
if not _reasoning_items and not _reasoning_tokens:
raise Exception(
"VALIDATION FAILED: reasoning stream - no reasoning output items or reasoning tokens in 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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
text={"format": {"type": "json_schema", "name": "CalendarEvent", "strict": True, "schema": response_schema}},
stream=True,
)
import json as _json
_accumulated = ""
for event in response:
if event.type == "response.output_text.delta":
_accumulated += event.delta
print(event.delta, 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
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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
text={"format": {"type": "json_schema", "name": "CalendarEvent", "strict": True, "schema": response_schema}},
stream=False,
)
import json as _json
_content = response.output_text
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 snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"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,
)
_tool_calls = [_item for _item in response.output if _item.type == "function_call"]
if not _tool_calls:
print(response.output_text)
print(f"Tools sent: {len(response.tools)}, tool_choice: {response.tool_choice}")
raise Exception(
"VALIDATION FAILED: tool-call - no tool calls in response"
)
for _tc in _tool_calls:
print(f"Function: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-terra",
input=[
{"role": "user", "content": "What is the capital of France?"},
],
stream=False,
)
print(response.output_text)
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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
text={"format": {"type": "json_schema", "name": "CalendarEvent", "strict": True, "schema": response_schema}},
stream=True,
)
import json as _json
_accumulated = ""
for event in response:
if event.type == "response.output_text.delta":
_accumulated += event.delta
print(event.delta, 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")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"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,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: parallel-tool-call stream - no completed response received"
)
_tool_calls = [_item for _item in _completed_response.output if _item.type == "function_call"]
if len(_tool_calls) < 1:
print(_completed_response.output_text)
print(f"Tools sent: {len(_completed_response.tools)}, tool_choice: {_completed_response.tool_choice}")
raise Exception(
f"VALIDATION FAILED: parallel-tool-call stream - expected at least 1 tool call, "
f"got {len(_tool_calls)}"
)
for _tc in _tool_calls:
print(f"\nFunction: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("\nVALIDATION: parallel-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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
text={"format": {"type": "json_schema", "name": "CalendarEvent", "strict": True, "schema": response_schema}},
stream=False,
)
import json as _json
_content = response.output_text
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 snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "What is the capital of France?"},
],
stream=False,
)
print(response.output_text)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"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,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: tool-call stream - no completed response received"
)
_tool_calls = [_item for _item in _completed_response.output if _item.type == "function_call"]
if not _tool_calls:
print(_completed_response.output_text)
print(f"Tools sent: {len(_completed_response.tools)}, tool_choice: {_completed_response.tool_choice}")
raise Exception(
"VALIDATION FAILED: tool-call stream - no tool calls in response"
)
for _tc in _tool_calls:
print(f"\nFunction: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "What is the capital of France?"},
],
stream=True,
)
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"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,
)
_tool_calls = [_item for _item in response.output if _item.type == "function_call"]
if len(_tool_calls) < 1:
print(response.output_text)
print(f"Tools sent: {len(response.tools)}, tool_choice: {response.tool_choice}")
raise Exception(
f"VALIDATION FAILED: parallel-tool-call - expected at least 1 tool call, "
f"got {len(_tool_calls)}"
)
for _tc in _tool_calls:
print(f"Function: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning={"effort": "medium"},
stream=True,
)
_completed_response = None
for event in response:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
if event.type == "response.completed":
_completed_response = event.response
if _completed_response is None:
raise Exception(
"VALIDATION FAILED: reasoning stream - no completed response received"
)
_reasoning_items = [
_item for _item in (getattr(_completed_response, "output", None) or [])
if getattr(_item, "type", None) == "reasoning"
]
_usage = getattr(_completed_response, "usage", None)
_details = getattr(_usage, "output_tokens_details", None) if _usage else None
_reasoning_tokens = getattr(_details, "reasoning_tokens", 0) if _details else 0
if not _reasoning_items and not _reasoning_tokens:
raise Exception(
"VALIDATION FAILED: reasoning stream - no reasoning output items or reasoning tokens in response"
)
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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
text={"format": {"type": "json_object"}},
stream=False,
)
import json as _json
_content = response.output_text
print(_content)
if not _content:
raise Exception("VALIDATION FAILED: json-output - response content is empty")
_json.loads(_content)
print("VALIDATION: json-output SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning={"effort": "medium"},
stream=False,
)
_reasoning_items = [
_item for _item in (getattr(response, "output", None) or [])
if getattr(_item, "type", None) == "reasoning"
]
_usage = getattr(response, "usage", None)
_details = getattr(_usage, "output_tokens_details", None) if _usage else None
_reasoning_tokens = getattr(_details, "reasoning_tokens", 0) if _details else 0
if response.output_text:
print(response.output_text)
if not _reasoning_items and not _reasoning_tokens:
raise Exception(
"VALIDATION FAILED: reasoning - no reasoning output items or reasoning tokens in 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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
text={"format": {"type": "json_object"}},
stream=True,
)
import json as _json
_accumulated = ""
for event in response:
if event.type == "response.output_text.delta":
_accumulated += event.delta
print(event.delta, end="", flush=True)
if not _accumulated:
raise Exception("VALIDATION FAILED: json-output stream - no content received")
_json.loads(_accumulated)
print("\nVALIDATION: json-output stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "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.responses.create(
model="test-v2-aws-bedrock-mantle/openai.gpt-5.6-luna",
input=[
{"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,
)
_tool_calls = [_item for _item in response.output if _item.type == "function_call"]
if not _tool_calls:
print(response.output_text)
print(f"Tools sent: {len(response.tools)}, tool_choice: {response.tool_choice}")
raise Exception(
"VALIDATION FAILED: tool-call - no tool calls in response"
)
for _tc in _tool_calls:
print(f"Function: {_tc.name}")
print(f"Arguments: {_tc.arguments}")
print("VALIDATION: tool-call SUCCESS") |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
| from: 272001 | ||
| output: | ||
| - cost_per_token: 0.0000495 | ||
| from: 272001 |
There was a problem hiding this comment.
Mismatched Sol pricing tier threshold
Low Severity
Sol’s new tiered_pricing uses from: 272001, but Luna and Terra in this same update use from: 272000, matching the other GPT-5.6 provider entries. At exactly 272000 input tokens, Sol would stay on base rates while the siblings switch to long-context rates.
Additional Locations (2)
Reviewed by Cursor Bugbot for commit 10c76d4. Configure here.
Contributor
|
/test-models |
Archit-Kumar-16
approved these changes
Aug 12, 2026
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
There are 2 total unresolved issues (including 1 from previous review).
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit d140429. Configure here.
| - json_output | ||
| limits: | ||
| context_window: 272000 | ||
| context_window: 1000000 |
There was a problem hiding this comment.
Incorrect context window limit
Medium Severity
context_window was changed from 1050000 to 1000000, which understates the model’s documented capacity. OpenAI lists gpt-5.6-luna at 1,050,000 tokens, and this file already sets max_input_tokens to 922000 with max_output_tokens of 128000, which only fits a 1050000 context. The lower value can cause valid long-context requests to be rejected or misrouted.
Reviewed by Cursor Bugbot for commit d140429. Configure here.
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
3 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
aws-bedrock-mantle.Note
Low Risk
Metadata-only provider catalog changes; incorrect tiers could affect cost estimates but no runtime or security impact.
Overview
Updates aws-bedrock-mantle catalog YAML for
openai.gpt-5.6-luna,openai.gpt-5.6-sol, andopenai.gpt-5.6-terrato reflect larger context and token-tier pricing.Limits:
context_windowrises from 272k to 1M on all three. Luna also addsmax_input_tokens(922k),max_output_tokens, andmax_tokens(128k). Terra drops the previousmax_input_tokens: 272000cap while keeping 128k output limits.Costs: Each regional cost block gains
tiered_pricingwithpricing_mode: cumulative—higher per-token rates for input, output, cache read, and cache write starting at 272000 (luna/terra) or 272001 (sol). Sol also nudges basecache_creation_input_token_costfrom0.00000688to0.000006875.Reviewed by Cursor Bugbot for commit d140429. Bugbot is set up for automated code reviews on this repo. Configure here.