Name	Type
model	str \| None
model_params	dict[str, Any]
profile_overrides	dict[str, Any]
model_context_limit	int \| None
classifier_model	str \| None
approval_mode	str
auto_approve	bool
approval_mode_key	str \| None
thread_id	str \| None
turn_id	str \| None
offload_tool_call_id	str \| None
hooks_snapshot_id	str \| None
hooks_server_events	list[str]
prompt_id	str \| None

attribute

model: str | None

Model spec to swap at runtime (e.g. 'provider:model').

attribute

model_params: dict[str, Any]

Invocation params (e.g. temperature, max_tokens) to merge into model_settings.

attribute

profile_overrides: dict[str, Any]

Model profile metadata supplied by --profile-override.

attribute

model_context_limit: int | None

Effective context-window limit for profile-aware middleware.

attribute

classifier_model: str | None

Model spec the Auto approval classifier should use for this run.

None (or absent) expresses no per-run preference, so the classifier keeps whatever the graph was built with — normally the main agent model, but a separate model when the session was launched with one. INHERIT_CLASSIFIER_MODEL overrides that startup value back to the main agent model. Set by /auto model so the switch takes effect without restarting the agent server.

attribute

approval_mode: str

manual, classifier-backed auto, or unrestricted yolo.

attribute

auto_approve: bool

Compatibility snapshot for clients predating the typed mode field.

attribute

approval_mode_key: str | None

Store key for the live approval-mode control record.

The TUI updates this record when the user toggles approval mode mid-run. The server-side interrupt predicate reads it from the LangGraph Store on each gated tool call so auto-to-manual changes can take effect before the current stream returns.

attribute

thread_id: str | None

LangGraph thread ID for the active conversation.

Mirrors config.configurable.thread_id into runtime context for model-call middleware that needs per-request session identity, including Fireworks session-affinity headers.

attribute

turn_id: str | None

Current user-turn ID for binding trusted interactive responses.

attribute

offload_tool_call_id: str | None

The sole tool-call ID authorized during a server-driven /offload run.

This is set by the client, not graph state, so model-generated calls cannot grant themselves permission to execute during the hidden compaction turn.

attribute

hooks_snapshot_id: str | None

Canonical Hooks v2 configuration hash for this session.

Server-owned lifecycle middleware includes this id on interrupt requests so the client can reject mismatched resumes.

attribute

hooks_server_events: list[str]

Server-owned HookEvent names that have configured handlers.

Middleware only interrupts for events listed here, avoiding a round-trip when the session snapshot has no matching handlers.

attribute

prompt_id: str | None

Optional per-turn prompt id projected into hook context.

Client-facing builder for the per-run graph context payload.

Callers populate this and pass it via context= to astream/ainvoke. ConfigurableModelMiddleware and the interrupt_on when predicate read it from request.runtime.context. In-process LangGraph coerces it into CLIContextSchema (the registered context_schema); over the API it stays a plain dict — which is why consumers handle both shapes.

Menu

CLIContext

Bases

Constructors

Attributes