Skip to content

LCORE-4827: Use new model in sources #2964

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tisnik merged 1 commit into from
Oct 19, 2026
+30 −30
Merged

LCORE-4827: Use new model in sources #2964

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 19 additions & 19 deletions docs/devel_doc/openapi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1439,7 +1439,7 @@
{
"config": {
"invalid_question_response": "I can only answer questions about the product.",
"model_id": "openai/gpt-4o-mini",
"model_id": "openai/gpt-5.6-luna",
"model_prompt": "Is this question valid?"
},
"name": "question-validity",
Expand Down Expand Up @@ -6110,7 +6110,7 @@
"model": {
"value": {
"detail": {
"cause": "Model with ID gpt-4o-mini does not exist",
"cause": "Model with ID gpt-5.6-luna does not exist",
"response": "Model not found"
}
}
Expand All @@ -6130,7 +6130,7 @@
"context window exceeded": {
"value": {
"detail": {
"cause": "The input exceeds the context window size of model 'gpt-4o-mini'.",
"cause": "The input exceeds the context window size of model 'gpt-5.6-luna'.",
"response": "Context window exceeded"
}
}
Expand Down Expand Up @@ -6487,7 +6487,7 @@
"model": {
"value": {
"detail": {
"cause": "Model with ID gpt-4o-mini does not exist",
"cause": "Model with ID gpt-5.6-luna does not exist",
"response": "Model not found"
}
}
Expand All @@ -6507,7 +6507,7 @@
"context window exceeded": {
"value": {
"detail": {
"cause": "The input exceeds the context window size of model 'gpt-4o-mini'.",
"cause": "The input exceeds the context window size of model 'gpt-5.6-luna'.",
"response": "Context window exceeded"
}
}
Expand Down Expand Up @@ -8536,7 +8536,7 @@
"type": "assistant"
}
],
"model": "gpt-4o-mini",
"model": "gpt-5.6-luna",
"provider": "openai",
"started_at": "2024-01-01T00:01:00Z",
"tool_calls": [],
Expand Down Expand Up @@ -9464,7 +9464,7 @@
"type": "assistant"
}
],
"model": "gpt-4o-mini",
"model": "gpt-5.6-luna",
"provider": "openai",
"started_at": "2024-01-01T00:01:00Z",
"tool_calls": [],
Expand Down Expand Up @@ -10362,7 +10362,7 @@
"model": {
"value": {
"detail": {
"cause": "Model with ID gpt-4o-mini does not exist",
"cause": "Model with ID gpt-5.6-luna does not exist",
"response": "Model not found"
}
}
Expand Down Expand Up @@ -10410,7 +10410,7 @@
"context window exceeded": {
"value": {
"detail": {
"cause": "The input exceeds the context window size of model 'gpt-4o-mini'.",
"cause": "The input exceeds the context window size of model 'gpt-5.6-luna'.",
"response": "Context window exceeded"
}
}
Expand Down Expand Up @@ -10732,7 +10732,7 @@
"model": {
"value": {
"detail": {
"cause": "Model with ID gpt-4o-mini does not exist",
"cause": "Model with ID gpt-5.6-luna does not exist",
"response": "Model not found"
}
}
Expand All @@ -10752,7 +10752,7 @@
"context window exceeded": {
"value": {
"detail": {
"cause": "The input exceeds the context window size of model 'gpt-4o-mini'.",
"cause": "The input exceeds the context window size of model 'gpt-5.6-luna'.",
"response": "Context window exceeded"
}
}
Expand Down Expand Up @@ -14103,7 +14103,7 @@
"type": "assistant"
}
],
"model": "gpt-4o-mini",
"model": "gpt-5.6-luna",
"provider": "openai",
"started_at": "2024-01-01T00:01:00Z",
"tool_calls": [],
Expand Down Expand Up @@ -14134,7 +14134,7 @@
"type": "assistant"
}
],
"model": "gpt-4o-mini",
"model": "gpt-5.6-luna",
"provider": "openai",
"started_at": "2024-01-01T00:01:00Z",
"tool_calls": [],
Expand Down Expand Up @@ -14184,7 +14184,7 @@
"title": "Model",
"description": "Model identifier used for this turn",
"examples": [
"gpt-4o-mini"
"gpt-5.6-luna"
]
},
"started_at": {
Expand Down Expand Up @@ -15266,7 +15266,7 @@
},
"type": "object",
"title": "Per-model context window sizes (tokens)",
"description": "Map of fully-qualified model identifier (e.g., \"openai/gpt-4o-mini\") to context window size in tokens. Used by the conversation compaction trigger to decide when older turns must be summarized before the input exceeds the window. Models absent from this map have no registered window \u2014 callers fall back to their own default or skip the token-based trigger."
"description": "Map of fully-qualified model identifier (e.g., \"openai/gpt-5.6-luna\") to context window size in tokens. Used by the conversation compaction trigger to decide when older turns must be summarized before the input exceeds the window. Models absent from this map have no registered window \u2014 callers fall back to their own default or skip the token-based trigger."
},
"providers": {
"items": {
Expand Down Expand Up @@ -16316,7 +16316,7 @@
},
{
"detail": {
"cause": "Model with ID gpt-4o-mini does not exist",
"cause": "Model with ID gpt-5.6-luna does not exist",
"response": "Model not found"
},
"label": "model"
Expand Down Expand Up @@ -18976,7 +18976,7 @@
"examples": [
{
"detail": {
"cause": "The input exceeds the context window size of model 'gpt-4o-mini'.",
"cause": "The input exceeds the context window size of model 'gpt-5.6-luna'.",
"response": "Context window exceeded"
},
"label": "context window exceeded"
Expand Down Expand Up @@ -20917,7 +20917,7 @@
"generate_topic_summary": true,
"input": "Hello World!",
"instructions": "You are a helpful assistant",
"model": "openai/gpt-4o-mini",
"model": "openai/gpt-5.6-luna",
"store": true,
"stream": false
}
Expand Down Expand Up @@ -22478,7 +22478,7 @@
{
"config": {
"invalid_question_response": "I can only answer questions about the product.",
"model_id": "openai/gpt-4o-mini",
"model_id": "openai/gpt-5.6-luna",
"model_prompt": "Is this question valid?"
},
"name": "question-validity",
Expand Down
2 changes: 1 addition & 1 deletion docs/models/successful_responses.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6021,7 +6021,7 @@
"available_quotas",
"output_text"
],
"sse_example": "event: response.created\ndata: {\"type\":\"response.created\",\"sequence_number\":0,\"response\":{\"id\":\"resp_abc\",\"object\":\"response\",\"created_at\":1704067200,\"status\":\"in_progress\",\"model\":\"openai/gpt-5.6-luna\",\"output\":[],\"store\":true,\"text\":{\"format\":{\"type\":\"text\"}},\"conversation\":\"0d21ba731f21f798dc9680125d5d6f49\",\"available_quotas\":{},\"output_text\":\"\"}}\n\nevent: response.output_item.added\ndata: {\"type\":\"response.output_item.added\",\"sequence_number\":1,\"response_id\":\"resp_abc\",\"output_index\":0,\"item\":{\"id\":\"msg_abc\",\"type\":\"message\",\"status\":\"in_progress\",\"role\":\"assistant\",\"content\":[]}}\n\n...\n\nevent: response.completed\ndata: {\"type\":\"response.completed\",\"sequence_number\":30,\"response\":{\"id\":\"resp_abc\",\"object\":\"response\",\"created_at\":1704067200,\"status\":\"completed\",\"model\":\"openai/gpt-5.6-luna\",\"output\":[{\"id\":\"msg_abc\",\"type\":\"message\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hello! How can I help?\",\"annotations\":[]}]}],\"store\":true,\"text\":{\"format\":{\"type\":\"text\"}},\"usage\":{\"input_tokens\":10,\"output_tokens\":6,\"total_tokens\":16,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens_details\":{\"reasoning_tokens\":0}},\"conversation\":\"0d21ba731f21f798dc9680125d5d6f49\",\"available_quotas\":{\"daily\":1000,\"monthly\":50000},\"output_text\":\"Hello! How can I help?\"}}\n\ndata: [DONE]\n\n",
"sse_example": "event: response.created\ndata: {\"type\":\"response.created\",\"sequence_number\":0,\"response\":{\"id\":\"resp_abc\",\"object\":\"response\",\"created_at\":1704067200,\"status\":\"in_progress\",\"model\":\"openai/gpt-4o-mini\",\"output\":[],\"store\":true,\"text\":{\"format\":{\"type\":\"text\"}},\"conversation\":\"0d21ba731f21f798dc9680125d5d6f49\",\"available_quotas\":{},\"output_text\":\"\"}}\n\nevent: response.output_item.added\ndata: {\"type\":\"response.output_item.added\",\"sequence_number\":1,\"response_id\":\"resp_abc\",\"output_index\":0,\"item\":{\"id\":\"msg_abc\",\"type\":\"message\",\"status\":\"in_progress\",\"role\":\"assistant\",\"content\":[]}}\n\n...\n\nevent: response.completed\ndata: {\"type\":\"response.completed\",\"sequence_number\":30,\"response\":{\"id\":\"resp_abc\",\"object\":\"response\",\"created_at\":1704067200,\"status\":\"completed\",\"model\":\"openai/gpt-4o-mini\",\"output\":[{\"id\":\"msg_abc\",\"type\":\"message\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hello! How can I help?\",\"annotations\":[]}]}],\"store\":true,\"text\":{\"format\":{\"type\":\"text\"}},\"usage\":{\"input_tokens\":10,\"output_tokens\":6,\"total_tokens\":16,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens_details\":{\"reasoning_tokens\":0}},\"conversation\":\"0d21ba731f21f798dc9680125d5d6f49\",\"available_quotas\":{\"daily\":1000,\"monthly\":50000},\"output_text\":\"Hello! How can I help?\"}}\n\ndata: [DONE]\n\n",
"title": "ResponsesResponse",
"type": "object"
},
Expand Down
2 changes: 1 addition & 1 deletion src/models/api/requests/responses_openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ class ResponsesRequest(BaseModel):
"examples": [
{
"input": "Hello World!",
"model": "openai/gpt-4o-mini",
"model": "openai/gpt-5.6-luna",
"instructions": "You are a helpful assistant",
"store": True,
"stream": False,
Expand Down
2 changes: 1 addition & 1 deletion src/models/api/responses/error/content_too_large.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ class PromptTooLongResponse(AbstractErrorResponse):
"response": "Context window exceeded",
"cause": (
"The input exceeds the context window size "
"of model 'gpt-4o-mini'."
"of model 'gpt-5.6-luna'."
),
},
},
Expand Down
2 changes: 1 addition & 1 deletion src/models/api/responses/error/not_found.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ class NotFoundResponse(AbstractErrorResponse):
"label": "model",
"detail": {
"response": "Model not found",
"cause": "Model with ID gpt-4o-mini does not exist",
"cause": "Model with ID gpt-5.6-luna does not exist",
},
},
{
Expand Down
2 changes: 1 addition & 1 deletion src/models/api/responses/successful/catalog.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ class ShieldsResponse(AbstractSuccessfulResponse):
"provider_id": "question_validity",
"type": "shield",
"config": {
"model_id": "openai/gpt-4o-mini",
"model_id": "openai/gpt-5.6-luna",
"model_prompt": "Is this question valid?",
"invalid_question_response": (
"I can only answer questions about the product."
Expand Down
4 changes: 2 additions & 2 deletions src/models/api/responses/successful/conversations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ class ConversationResponse(AbstractSuccessfulResponse):
"tool_calls": [],
"tool_results": [],
"provider": "openai",
"model": "gpt-4o-mini",
"model": "gpt-5.6-luna",
"started_at": "2024-01-01T00:01:00Z",
"completed_at": "2024-01-01T00:01:05Z",
}
Expand All @@ -67,7 +67,7 @@ class ConversationResponse(AbstractSuccessfulResponse):
"tool_calls": [],
"tool_results": [],
"provider": "openai",
"model": "gpt-4o-mini",
"model": "gpt-5.6-luna",
"started_at": "2024-01-01T00:01:00Z",
"completed_at": "2024-01-01T00:01:05Z",
}
Expand Down
2 changes: 1 addition & 1 deletion src/models/common/conversation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ class ConversationTurn(BaseModel):
model: str = Field(
...,
description="Model identifier used for this turn",
examples=["gpt-4o-mini"],
examples=["gpt-5.6-luna"],
)
started_at: str = Field(
...,
Expand Down
2 changes: 1 addition & 1 deletion src/models/compaction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ class ConversationSummary(BaseModel):
produced. Kept as a string (not datetime) to match the
cache schema convention used elsewhere in the codebase.
model_used: Fully-qualified model identifier used for the
summarization LLM call (e.g., ``"openai/gpt-4o-mini"``).
summarization LLM call (e.g., ``"openai/gpt-5.6-luna"``).
Preserved for audit and for diagnostics when summary
quality varies between models.

Expand Down
2 changes: 1 addition & 1 deletion src/models/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2053,7 +2053,7 @@ class InferenceConfiguration(ConfigurationBase):
default_factory=dict,
title="Per-model context window sizes (tokens)",
description="Map of fully-qualified model identifier (e.g., "
'"openai/gpt-4o-mini") to context window size in tokens. Used by '
'"openai/gpt-5.6-luna") to context window size in tokens. Used by '
"the conversation compaction trigger to decide when older turns "
"must be summarized before the input exceeds the window. Models "
"absent from this map have no registered window — callers fall "
Expand Down
2 changes: 1 addition & 1 deletion src/pydantic_ai_lightspeed/capabilities/question_validity/_capability.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ class QuestionValidity(AbstractSafetyCapability):
from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIResponsesModel

model = OpenAIResponsesModel("gpt-4o-mini")
model = OpenAIResponsesModel("gpt-5.6-luna")
agent = Agent("openai:gpt-4.1", capabilities=[QuestionValidity(model)])
```

Expand Down
Loading