---
sidebar:
  hidden: true
title: roboto.ai.goals.achieve_inputs
---
Pydantic models for the inputs an achieve-tool receives from the LLM.

Each model captures the exact JSON shape the LLM submits when invoking the achieve-tool for a goal of the corresponding [`GoalType`](/docs/reference/python-sdk/roboto/ai/goals#roboto.ai.goals.GoalType). The models are shared between the server-side handlers (which validate the LLM's `tool_use` `input` against them) and the SDK-side [`roboto.ai.goals.results`](/docs/reference/python-sdk/roboto/ai/goals/results) `GoalResult` discriminated union (which re-hydrates the same shape from the persisted message stream).

Vocabulary-aware constraints (e.g. "label must be one of the goal's declared labels", "event name must be in the goal's event vocabulary") are not expressible at the static-model level because they depend on the goal instance; the server-side handler enforces them as a second pass after this structural validation. The SDK does not enforce them at all — historical `tool_use` inputs have already passed both Bedrock's schema check and the handler's vocab check at the time they were persisted.

## Module Contents

### CreateEventsAchieveInput

```python
class roboto.ai.goals.achieve_inputs.CreateEventsAchieveInput(/, **data: Any)
```

`from roboto.ai.goals import CreateEventsAchieveInput`

[Source](https://github.com/roboto-ai/roboto-python-sdk/blob/main/src/roboto/ai/goals/achieve_inputs.py#L173-L178)

Bases: `pydantic.BaseModel`

Input the LLM submits to achieve a [`GoalType.CREATE_EVENTS`](/reference/python-sdk/roboto/ai/goals/types#roboto.ai.goals.types.GoalType.CREATE_EVENTS) goal.

**Parameters**

- **data** (`Any`)

**Attributes**

- **CreateEventsAchieveInput.events** (`list[EventSpec]`): The events to create. May be empty if the agent found no intervals matching the declared event types.

### DatasetSummaryAchieveInput

```python
class roboto.ai.goals.achieve_inputs.DatasetSummaryAchieveInput(/, **data: Any)
```

`from roboto.ai.goals import DatasetSummaryAchieveInput`

[Source](https://github.com/roboto-ai/roboto-python-sdk/blob/main/src/roboto/ai/goals/achieve_inputs.py#L43-L56)

Bases: `pydantic.BaseModel`

Input the LLM submits to achieve a [`GoalType.DATASET_SUMMARY`](/reference/python-sdk/roboto/ai/goals/types#roboto.ai.goals.types.GoalType.DATASET_SUMMARY) goal.

**Parameters**

- **data** (`Any`)

**Attributes**

- **DatasetSummaryAchieveInput.summary** (`str`) = `None`: The full natural-language summary to persist for the dataset.

  Must contain non-whitespace characters; the achieve-tool rejects pure whitespace as equivalent to empty.

### DatasetTriageAchieveInput

```python
class roboto.ai.goals.achieve_inputs.DatasetTriageAchieveInput(/, **data: Any)
```

`from roboto.ai.goals import DatasetTriageAchieveInput`

[Source](https://github.com/roboto-ai/roboto-python-sdk/blob/main/src/roboto/ai/goals/achieve_inputs.py#L98-L108)

Bases: `pydantic.BaseModel`

Input the LLM submits to achieve a [`GoalType.DATASET_TRIAGE`](/reference/python-sdk/roboto/ai/goals/types#roboto.ai.goals.types.GoalType.DATASET_TRIAGE) goal.

**Parameters**

- **data** (`Any`)

**Attributes**

- **DatasetTriageAchieveInput.label_decisions** (`list[LabelDecision]`) = `None`: One [`LabelDecision`](/reference/python-sdk/roboto/ai/goals/achieve_inputs#roboto.ai.goals.achieve_inputs.LabelDecision) per entry in the goal's `label_vocabulary`.

  Vocabulary completeness — every label declared on the goal appears exactly once, with no duplicates — is enforced by the server-side handler. This model only validates the structural shape of each decision.

### EventSpec

```python
class roboto.ai.goals.achieve_inputs.EventSpec(/, **data: Any)
```

`from roboto.ai.goals import EventSpec`

[Source](https://github.com/roboto-ai/roboto-python-sdk/blob/main/src/roboto/ai/goals/achieve_inputs.py#L111-L170)

Bases: `pydantic.BaseModel`

One event the LLM proposes inside a [`CreateEventsAchieveInput`](/reference/python-sdk/roboto/ai/goals/achieve_inputs#roboto.ai.goals.achieve_inputs.CreateEventsAchieveInput).

The `name` must come from the parent goal's `event_vocabulary` and every `tags` entry from the goal's `tag_vocabulary`; both checks live in the server-side handler because they depend on the goal instance.

**Parameters**

- **data** (`Any`)

**Attributes**

- **EventSpec.description** (`str | None`) = `None`: Optional longer explanation of what the event captures.

- **EventSpec.end_time** (`pydantic.StrictInt`): Event end, in nanoseconds since the Unix epoch. Must be greater than or equal to [`start_time`](/reference/python-sdk/roboto/ai/goals/achieve_inputs#roboto.ai.goals.achieve_inputs.EventSpec.start_time).

  Strictly typed for the same reason as [`start_time`](/reference/python-sdk/roboto/ai/goals/achieve_inputs#roboto.ai.goals.achieve_inputs.EventSpec.start_time).

- **EventSpec.name** (`str`): The kind of event. Must be one of the goal's declared event vocabulary names (enforced by the handler).

- **EventSpec.start_time** (`pydantic.StrictInt`): Event start, in nanoseconds since the Unix epoch.

  Strictly typed: pydantic would otherwise coerce stringified integers and (notably) booleans — `True` would silently parse as timestamp 1. The historical achieve-tool contract required a JSON integer.

- **EventSpec.tags** (`list[str]`) = `None`: Tags attached to this event. Each must be one of the goal's declared tag vocabulary keys (enforced by the handler). Empty by default.

- **EventSpec.target_id** (`str | None`) = `None`: Identifier of the Roboto entity this event is attached to. The server-side handler infers the entity type from the id prefix (`ds_` / `fl_` / `tp_` / `mp_`) and enforces that the target descends from the goal's dataset.

  Optional rather than required so the SDK can re-hydrate `CreateEventsGoalResult` from persisted tool-use records written before per-event target scoping was added — those carry no `target_id` on each spec. Current-day records always carry a non-empty value; the handler rejects `None` on new invocations via a corrective tool-failure response.

### LabelDecision

```python
class roboto.ai.goals.achieve_inputs.LabelDecision(/, **data: Any)
```

`from roboto.ai.goals import LabelDecision`

[Source](https://github.com/roboto-ai/roboto-python-sdk/blob/main/src/roboto/ai/goals/achieve_inputs.py#L59-L95)

Bases: `pydantic.BaseModel`

One per-label deliberation entry inside a [`DatasetTriageAchieveInput`](/reference/python-sdk/roboto/ai/goals/achieve_inputs#roboto.ai.goals.achieve_inputs.DatasetTriageAchieveInput).

Every label in the goal's `label_vocabulary` must appear exactly once across the parent `label_decisions` list — that constraint is enforced by the server-side handler after structural validation, since the vocabulary is goal-instance-specific.

**Parameters**

- **data** (`Any`)

**Attributes**

- **LabelDecision.applies** (`pydantic.StrictBool`): Whether the label applies to the dataset. `True` decisions become tags on the dataset; `False` decisions are recorded in the tool-use log but not persisted on the dataset itself.

  Strictly typed to reject pydantic's default truthy-string coercion — the historical achieve-tool contract required a JSON boolean, not a boolean-coerced string or integer.

- **LabelDecision.confidence** (`float`) = `None`: Subjective confidence in the decision, from 0.0 (no confidence) to 1.0 (certain). Recorded but not used to gate persistence.

- **LabelDecision.justification** (`str`) = `None`: Brief reasoning for the decision, citing concrete observations from the dataset. Required even when `applies` is `False` so the deliberation is captured.

- **LabelDecision.label** (`str`): The vocabulary label this decision concerns. Must match one of the goal's `label_vocabulary` keys (enforced by the handler against the declaring goal).