SurfSense/surfsense_backend/app/automations/schemas/actions/agent_task.py

28 lines
886 B
Python
Raw Normal View History

feat(automation): add Pydantic schemas for the automation definition Three layers of Pydantic models under app/automations/schemas/, one file per concern (SRP), matching the envelope in automation-design-plan.md §5. definition/ — the editable envelope persisted in automations.definition: - envelope.py AutomationDefinition (top-level shape) - plan_step.py PlanStep (one step in the sequential plan) - inputs.py InputsBlock (the inputs JSON Schema wrapper) - execution.py ExecutionBlock (timeouts, retries, concurrency, budget cap, on_failure plan) - metadata.py MetadataBlock (tags + created_from_nl + extras) - trigger_spec.py TriggerSpec (one entry in triggers[]) triggers/ — per-trigger config schemas, dispatched by registry on the TriggerSpec.type discriminator: - schedule.py ScheduleTriggerConfig(cron, timezone) - manual.py ManualTriggerConfig() — empty in v1 actions/ — per-action config schemas, dispatched by registry on the PlanStep.action discriminator: - agent_task.py AgentTaskActionConfig(prompt, tools, model, output_schema) Design properties verified by an inline smoke test: - The §5 worked example round-trips through model_validate_json / model_dump_json byte-for-byte (InputsBlock uses serialize_by_alias so the JSON key stays "schema" not "schema_"). - Envelope rejects unknown top-level keys (extra="forbid"). - MetadataBlock tolerates unknown keys (extra="allow"). - ExecutionBlock defaults apply when the block is omitted. - retry_backoff and concurrency are typed as Literal — bogus values rejected at validation time. - Per-type configs enforce their required fields (cron + timezone on schedule; non-empty prompt on agent_task). The envelope keeps trigger and action configs as untyped dicts on purpose — per-type validation is a registry-driven dispatch (commit 10), keeping the envelope free of every-type-knows-every-type coupling.
2026-05-26 22:50:52 +02:00
"""``AgentTaskActionConfig`` — config for the ``agent_task`` action type."""
from __future__ import annotations
from typing import Any
from pydantic import BaseModel, ConfigDict, Field
class AgentTaskActionConfig(BaseModel):
"""Run a LangGraph Deep Agent restricted to a scoped capability list."""
feat(automation): add Pydantic schemas for the automation definition Three layers of Pydantic models under app/automations/schemas/, one file per concern (SRP), matching the envelope in automation-design-plan.md §5. definition/ — the editable envelope persisted in automations.definition: - envelope.py AutomationDefinition (top-level shape) - plan_step.py PlanStep (one step in the sequential plan) - inputs.py InputsBlock (the inputs JSON Schema wrapper) - execution.py ExecutionBlock (timeouts, retries, concurrency, budget cap, on_failure plan) - metadata.py MetadataBlock (tags + created_from_nl + extras) - trigger_spec.py TriggerSpec (one entry in triggers[]) triggers/ — per-trigger config schemas, dispatched by registry on the TriggerSpec.type discriminator: - schedule.py ScheduleTriggerConfig(cron, timezone) - manual.py ManualTriggerConfig() — empty in v1 actions/ — per-action config schemas, dispatched by registry on the PlanStep.action discriminator: - agent_task.py AgentTaskActionConfig(prompt, tools, model, output_schema) Design properties verified by an inline smoke test: - The §5 worked example round-trips through model_validate_json / model_dump_json byte-for-byte (InputsBlock uses serialize_by_alias so the JSON key stays "schema" not "schema_"). - Envelope rejects unknown top-level keys (extra="forbid"). - MetadataBlock tolerates unknown keys (extra="allow"). - ExecutionBlock defaults apply when the block is omitted. - retry_backoff and concurrency are typed as Literal — bogus values rejected at validation time. - Per-type configs enforce their required fields (cron + timezone on schedule; non-empty prompt on agent_task). The envelope keeps trigger and action configs as untyped dicts on purpose — per-type validation is a registry-driven dispatch (commit 10), keeping the envelope free of every-type-knows-every-type coupling.
2026-05-26 22:50:52 +02:00
model_config = ConfigDict(extra="forbid")
prompt: str = Field(..., min_length=1, description="Task prompt; Jinja-rendered.")
feat(automation): add Pydantic schemas for the automation definition Three layers of Pydantic models under app/automations/schemas/, one file per concern (SRP), matching the envelope in automation-design-plan.md §5. definition/ — the editable envelope persisted in automations.definition: - envelope.py AutomationDefinition (top-level shape) - plan_step.py PlanStep (one step in the sequential plan) - inputs.py InputsBlock (the inputs JSON Schema wrapper) - execution.py ExecutionBlock (timeouts, retries, concurrency, budget cap, on_failure plan) - metadata.py MetadataBlock (tags + created_from_nl + extras) - trigger_spec.py TriggerSpec (one entry in triggers[]) triggers/ — per-trigger config schemas, dispatched by registry on the TriggerSpec.type discriminator: - schedule.py ScheduleTriggerConfig(cron, timezone) - manual.py ManualTriggerConfig() — empty in v1 actions/ — per-action config schemas, dispatched by registry on the PlanStep.action discriminator: - agent_task.py AgentTaskActionConfig(prompt, tools, model, output_schema) Design properties verified by an inline smoke test: - The §5 worked example round-trips through model_validate_json / model_dump_json byte-for-byte (InputsBlock uses serialize_by_alias so the JSON key stays "schema" not "schema_"). - Envelope rejects unknown top-level keys (extra="forbid"). - MetadataBlock tolerates unknown keys (extra="allow"). - ExecutionBlock defaults apply when the block is omitted. - retry_backoff and concurrency are typed as Literal — bogus values rejected at validation time. - Per-type configs enforce their required fields (cron + timezone on schedule; non-empty prompt on agent_task). The envelope keeps trigger and action configs as untyped dicts on purpose — per-type validation is a registry-driven dispatch (commit 10), keeping the envelope free of every-type-knows-every-type coupling.
2026-05-26 22:50:52 +02:00
tools: list[str] = Field(
default_factory=list,
description="Capability IDs the agent may call. Empty = no tool access.",
feat(automation): add Pydantic schemas for the automation definition Three layers of Pydantic models under app/automations/schemas/, one file per concern (SRP), matching the envelope in automation-design-plan.md §5. definition/ — the editable envelope persisted in automations.definition: - envelope.py AutomationDefinition (top-level shape) - plan_step.py PlanStep (one step in the sequential plan) - inputs.py InputsBlock (the inputs JSON Schema wrapper) - execution.py ExecutionBlock (timeouts, retries, concurrency, budget cap, on_failure plan) - metadata.py MetadataBlock (tags + created_from_nl + extras) - trigger_spec.py TriggerSpec (one entry in triggers[]) triggers/ — per-trigger config schemas, dispatched by registry on the TriggerSpec.type discriminator: - schedule.py ScheduleTriggerConfig(cron, timezone) - manual.py ManualTriggerConfig() — empty in v1 actions/ — per-action config schemas, dispatched by registry on the PlanStep.action discriminator: - agent_task.py AgentTaskActionConfig(prompt, tools, model, output_schema) Design properties verified by an inline smoke test: - The §5 worked example round-trips through model_validate_json / model_dump_json byte-for-byte (InputsBlock uses serialize_by_alias so the JSON key stays "schema" not "schema_"). - Envelope rejects unknown top-level keys (extra="forbid"). - MetadataBlock tolerates unknown keys (extra="allow"). - ExecutionBlock defaults apply when the block is omitted. - retry_backoff and concurrency are typed as Literal — bogus values rejected at validation time. - Per-type configs enforce their required fields (cron + timezone on schedule; non-empty prompt on agent_task). The envelope keeps trigger and action configs as untyped dicts on purpose — per-type validation is a registry-driven dispatch (commit 10), keeping the envelope free of every-type-knows-every-type coupling.
2026-05-26 22:50:52 +02:00
)
model: str | None = Field(
default=None,
description="LiteLLM model id. Defaults to the search space's agent_llm_id.",
feat(automation): add Pydantic schemas for the automation definition Three layers of Pydantic models under app/automations/schemas/, one file per concern (SRP), matching the envelope in automation-design-plan.md §5. definition/ — the editable envelope persisted in automations.definition: - envelope.py AutomationDefinition (top-level shape) - plan_step.py PlanStep (one step in the sequential plan) - inputs.py InputsBlock (the inputs JSON Schema wrapper) - execution.py ExecutionBlock (timeouts, retries, concurrency, budget cap, on_failure plan) - metadata.py MetadataBlock (tags + created_from_nl + extras) - trigger_spec.py TriggerSpec (one entry in triggers[]) triggers/ — per-trigger config schemas, dispatched by registry on the TriggerSpec.type discriminator: - schedule.py ScheduleTriggerConfig(cron, timezone) - manual.py ManualTriggerConfig() — empty in v1 actions/ — per-action config schemas, dispatched by registry on the PlanStep.action discriminator: - agent_task.py AgentTaskActionConfig(prompt, tools, model, output_schema) Design properties verified by an inline smoke test: - The §5 worked example round-trips through model_validate_json / model_dump_json byte-for-byte (InputsBlock uses serialize_by_alias so the JSON key stays "schema" not "schema_"). - Envelope rejects unknown top-level keys (extra="forbid"). - MetadataBlock tolerates unknown keys (extra="allow"). - ExecutionBlock defaults apply when the block is omitted. - retry_backoff and concurrency are typed as Literal — bogus values rejected at validation time. - Per-type configs enforce their required fields (cron + timezone on schedule; non-empty prompt on agent_task). The envelope keeps trigger and action configs as untyped dicts on purpose — per-type validation is a registry-driven dispatch (commit 10), keeping the envelope free of every-type-knows-every-type coupling.
2026-05-26 22:50:52 +02:00
)
output_schema: dict[str, Any] | None = Field(
default=None,
description="JSON Schema the agent must return. Recommended.",
feat(automation): add Pydantic schemas for the automation definition Three layers of Pydantic models under app/automations/schemas/, one file per concern (SRP), matching the envelope in automation-design-plan.md §5. definition/ — the editable envelope persisted in automations.definition: - envelope.py AutomationDefinition (top-level shape) - plan_step.py PlanStep (one step in the sequential plan) - inputs.py InputsBlock (the inputs JSON Schema wrapper) - execution.py ExecutionBlock (timeouts, retries, concurrency, budget cap, on_failure plan) - metadata.py MetadataBlock (tags + created_from_nl + extras) - trigger_spec.py TriggerSpec (one entry in triggers[]) triggers/ — per-trigger config schemas, dispatched by registry on the TriggerSpec.type discriminator: - schedule.py ScheduleTriggerConfig(cron, timezone) - manual.py ManualTriggerConfig() — empty in v1 actions/ — per-action config schemas, dispatched by registry on the PlanStep.action discriminator: - agent_task.py AgentTaskActionConfig(prompt, tools, model, output_schema) Design properties verified by an inline smoke test: - The §5 worked example round-trips through model_validate_json / model_dump_json byte-for-byte (InputsBlock uses serialize_by_alias so the JSON key stays "schema" not "schema_"). - Envelope rejects unknown top-level keys (extra="forbid"). - MetadataBlock tolerates unknown keys (extra="allow"). - ExecutionBlock defaults apply when the block is omitted. - retry_backoff and concurrency are typed as Literal — bogus values rejected at validation time. - Per-type configs enforce their required fields (cron + timezone on schedule; non-empty prompt on agent_task). The envelope keeps trigger and action configs as untyped dicts on purpose — per-type validation is a registry-driven dispatch (commit 10), keeping the envelope free of every-type-knows-every-type coupling.
2026-05-26 22:50:52 +02:00
)