User Intent¶
Cluster: Uncategorised | Type: component | MCP Tools: 4
Overview¶
Public API¶
UserIntentDecisionError(ValueError)¶
The LLM did not produce a usable, validated intent decision.
IntentDecision¶
Validated intent-endorsement verdict.
| Field | Type | Default |
|---|---|---|
posture | str | required |
baseline_posture | str | required |
requires_confirmation | bool | required |
baseline_requires_confirmation | bool | required |
literal_interpretation | str | '' |
extrapolated_interpretation | str | '' |
baseline_extrapolation | str | '' |
divergence_summary | str | '' |
degraded | bool | False |
llm_used | bool | False |
reasons | tuple[str, ...] | () |
rationale | str | '' |
raw_response | str | '' |
Methods:
escalated() -> bool¶
extrapolation_enriched() -> bool¶
agentic_evidence() -> dict[str, Any]¶
to_dict() -> dict[str, Any]¶
to_endorsed_intent() -> EndorsedIntent¶
Build an EndorsedIntent from the FINAL (post-clamp) fields.
UserIntentPlanner¶
Runtime-first facade with deterministic fallback + one-way posture clamp.
| Field | Type | Default |
|---|---|---|
runtime | UserIntentRuntime \| None | None |
last_decision | IntentDecision \| None | field(default=None, init=False) |
last_llm_used | bool | field(default=False, init=False) |
last_fallback_reason | str | field(default='', init=False) |
Methods:
interpret(literal_request: str, context: str = '', risks: list[str] | None = None) -> IntentDecision¶
UserIntentInput(BaseModel)¶
| Field | Type | Default |
|---|---|---|
op | Literal['interpret', 'record_explicit', 'infer_from_behavior', 'get', 'reset', 'list', 'ops', 'help'] | 'interpret' |
literal_request | str | '' |
context | str | '' |
risks | list[str] | [] |
key | str | '' |
value | str | '' |
event | str | '' |
preference_path | str | '.g6/memory/user_preferences.yaml' |
UserIntentBlock(AIBlock[UserIntentInput, dict, dict])¶
Constructor:
| Parameter | Type | Default |
|---|---|---|
name | str | 'user_intent' |
state | dict \| None | None |
Methods:
infer(data: UserIntentInput) -> Result[dict]¶
EndorsedIntent(BaseModel)¶
| Field | Type | Default |
|---|---|---|
literal_interpretation | str | required |
extrapolated_interpretation | str | required |
divergence_summary | str | '' |
requires_confirmation | bool | False |
UserExtrapolatedIntent¶
Methods:
interpret(literal_request: str, context: str = '', risks: list[str] | None = None) -> EndorsedIntent¶
UserIntentPatternRuntime¶
Stateless executable mechanisms for user_intent's applied patterns.
Methods:
tighten(posture: Any, baseline_posture: Any = '', requires_confirmation: bool = False, baseline_requires_confirmation: bool = False, degraded: bool = False, risks_present: bool = False, divergence_detected: bool = False) -> UserIntentPatternReview¶
One-way endorsement-posture guard (hook-based-safety-guard-rails).
Preference(BaseModel)¶
| Field | Type | Default |
|---|---|---|
key | str | required |
value | str | required |
source | Literal['explicit', 'inferred'] | required |
confidence | float | required |
evidence_count | int | 1 |
PreferenceUncertaintyModel¶
Constructor:
| Parameter | Type | Default |
|---|---|---|
path | str \| Path | '.g6/memory/user_preferences.yaml' |
Methods:
record_explicit(key: str, value: str) -> Preference¶
infer_from_behavior(event: str) -> Preference¶
get(key: str) -> Preference | None¶
reset(key: str) -> None¶
list() -> list[Preference]¶
save() -> Path¶
Functions¶
deterministic_intent_decision(literal_request: str, context: str = '', risks: list[str] | None = None) -> IntentDecision¶
Demoted-real STRUCTURAL baseline (the zero-LLM floor).
apply_intent_floor(baseline: IntentDecision, candidate_posture: Any) -> IntentDecision¶
One-way endorsement-posture safety clamp (stricter-of, ESCALATE only).
build_default_planner() -> 'UserIntentPlanner | None'¶
Build the on-by-default agentic planner, or None when suppressed.
grounded_interpret_intent(literal_request: str, context: str = '', risks: list[str] | None = None, planner: UserIntentPlanner | None = None) -> IntentDecision¶
The ONE shared grounded chokepoint for EVERY user_intent interpret decision.
applied_agentic_patterns() -> list[dict[str, Any]]¶
Return compact metadata for user_intent-applied vendored patterns.
MCP Tools¶
| Operation | Source |
|---|---|
ops | user_intent_mcp |
help | user_intent_mcp |
interpret | user_intent_mcp |
list_patterns | user_intent_mcp |