dlgforge.llm

Public exports for LLM settings and client helpers.

ChatResult(content, tool_calls, raw) dataclass

Normalized chat completion output.

OpenAIModelClient()

OpenAI-compatible public client, backed internally by LiteLLM.

missing_models(cfg)

Return missing models.

Parameters:

Name	Type	Description	Default
cfg	Dict[str, Any]	Configuration mapping that controls runtime behavior.	required

Returns:

Type	Description
List[str]	List[str]: Value produced by this API.

Raises:

Type	Description
Exception	Propagates unexpected runtime errors from downstream calls.

Side Effects / I/O: - Primarily performs in-memory transformations.

Preconditions / Invariants: - Callers should provide arguments matching annotated types and expected data contracts.

Examples:

>>> from dlgforge.llm.settings import missing_models
>>> missing_models(...)

required_agents(cfg)

Return required agents.

Parameters:

Name	Type	Description	Default
cfg	Dict[str, Any]	Configuration mapping that controls runtime behavior.	required

Returns:

Type	Description
List[str]	List[str]: Value produced by this API.

Raises:

Type	Description
Exception	Propagates unexpected runtime errors from downstream calls.

Side Effects / I/O: - Primarily performs in-memory transformations.

Preconditions / Invariants: - Callers should provide arguments matching annotated types and expected data contracts.

Examples:

>>> from dlgforge.llm.settings import required_agents
>>> required_agents(...)

resolve_agent_used_name(cfg, agent_key)

Resolve agent used name.

Parameters:

Name	Type	Description	Default
cfg	Dict[str, Any]	Configuration mapping that controls runtime behavior.	required
agent_key	str	str value used by this operation.	required

Returns:

Name	Type	Description
str	str	Resolved value after applying defaults and normalization rules.

Raises:

Type	Description
Exception	Propagates unexpected runtime errors from downstream calls.

Side Effects / I/O: - Primarily performs in-memory transformations.

Preconditions / Invariants: - Callers should provide arguments matching annotated types and expected data contracts.

Examples:

>>> from dlgforge.llm.settings import resolve_agent_used_name
>>> resolve_agent_used_name(...)

resolve_llm_settings(cfg, agent_key)

Resolve llm settings from configuration.

Parameters:

Name	Type	Description	Default
cfg	Dict[str, Any]	Configuration mapping that controls runtime behavior.	required
agent_key	str	str value used by this operation.	required

Returns:

Type	Description
Dict[str, Any]	Dict[str, Any]: Resolved value after applying defaults and normalization rules.

Raises:

Type	Description
Exception	Propagates unexpected runtime errors from downstream calls.

Side Effects / I/O: - Primarily performs in-memory transformations.

Preconditions / Invariants: - Callers should provide arguments matching annotated types and expected data contracts.

Examples:

>>> from dlgforge.llm.settings import resolve_llm_settings
>>> resolve_llm_settings(...)