A cascade has no end worth recording; a run does. Parameters go in, the graph executes until it drains, and the result is kept — which is what an ML experiment is and what a CI-style job is, so both are one entity. Each run gets a state backend namespaced to itself, so two runs of one flow cannot overwrite each other's messages; that is a constructor argument rather than a change to the pipeline, because every key the engine keeps already goes through the state backend. Its record is written by the driver thread rather than folded off the event bus, which drops what it cannot keep up with. Its own Redis stream wakes an engine up, and from the claim onwards the database row is the truth: redelivering hours of training because an acknowledgement was late is not recovery, so a stale lease is what marks a run whose engine died. Flows gain mode: batch, which are built and validated but never activated, and nodes gain a device label for the worker that must run them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AD8SfVhzXBG2nAfFcVh3iD
272 lines
7.7 KiB
Python
272 lines
7.7 KiB
Python
"""The persisted shape of a flow, shared by the store, the API and the editor.
|
|
|
|
A flow is structure plus code: this module is the structure. Node logic for
|
|
``python`` nodes lives beside it as a plain ``.py`` file.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
from typing import Any, Literal
|
|
|
|
from pydantic import BaseModel, Field, field_validator
|
|
|
|
from app.flow.messages import MessageSpec
|
|
|
|
NAME_PATTERN = re.compile(r"^[a-z][a-z0-9_]*$")
|
|
|
|
|
|
def _validate_name(value: str) -> str:
|
|
if not NAME_PATTERN.match(value):
|
|
raise ValueError(
|
|
"Use lowercase letters, digits and underscores, starting with a letter"
|
|
)
|
|
return value
|
|
|
|
|
|
class NodeDef(BaseModel):
|
|
"""A node as stored: identity, configuration and ports.
|
|
|
|
Deliberately no canvas position. The editor lays a flow out itself, so
|
|
where a node sits is a fact about the drawing rather than about the flow —
|
|
and a graph nobody can arrange is one worth keeping small.
|
|
"""
|
|
|
|
id: str
|
|
type: str = "python"
|
|
title: str = ""
|
|
params: dict[str, Any] = Field(default_factory=dict)
|
|
requires: list[MessageSpec] = Field(default_factory=list)
|
|
provides: list[MessageSpec] = Field(default_factory=list)
|
|
#: Name of a shared source in the library, instead of this node's own file.
|
|
#: Editing it edits the copy every flow using it runs.
|
|
source_ref: str | None = None
|
|
timeout: float | None = Field(
|
|
default=None,
|
|
gt=0,
|
|
description=(
|
|
"Seconds this node's code may run before it is stopped. This "
|
|
"covers the first call's imports, which can be much slower than "
|
|
"the body. Above 60 the engine may deliver its work again while "
|
|
"it is still running — in a batch run, which never redelivers, "
|
|
"it is an idle timeout instead: silence this long is a kill."
|
|
),
|
|
)
|
|
device: str | None = Field(
|
|
default=None,
|
|
description=(
|
|
"Label of the worker this node's code must run on, such as 'gpu'. "
|
|
"Empty means the engine's own workers. A run needing a label no "
|
|
"attached worker carries waits rather than failing."
|
|
),
|
|
)
|
|
device_policy: Literal["require", "prefer"] = Field(
|
|
default="require",
|
|
description=(
|
|
"What to do when no worker carries `device`: wait for one, or run "
|
|
"locally anyway."
|
|
),
|
|
)
|
|
|
|
@field_validator("id")
|
|
@classmethod
|
|
def _check_id(cls, value: str) -> str:
|
|
return _validate_name(value)
|
|
|
|
|
|
class FlowInput(BaseModel):
|
|
"""A message the flow starts with rather than computes."""
|
|
|
|
spec: MessageSpec
|
|
initial: Any | None = None
|
|
|
|
|
|
class FlowDef(BaseModel):
|
|
"""One atomic flow."""
|
|
|
|
name: str
|
|
title: str = ""
|
|
nodes: list[NodeDef] = Field(default_factory=list)
|
|
inputs: list[FlowInput] = Field(default_factory=list)
|
|
version: int = 1
|
|
mode: Literal["live", "batch"] = Field(
|
|
default="live",
|
|
description=(
|
|
"A live flow reacts to what arrives: its subscriptions, schedules "
|
|
"and webhooks run until it is stopped. A batch flow only runs when "
|
|
"a run asks it to, from its inputs to its outputs, and is never "
|
|
"activated."
|
|
),
|
|
)
|
|
outputs: list[str] = Field(
|
|
default_factory=list,
|
|
description=(
|
|
"Messages a batch run reports as its result, unqualified. Empty "
|
|
"means every message the flow ends up holding."
|
|
),
|
|
)
|
|
|
|
@field_validator("name")
|
|
@classmethod
|
|
def _check_name(cls, value: str) -> str:
|
|
return _validate_name(value)
|
|
|
|
|
|
class NodeSource(BaseModel):
|
|
"""The Python source of a node."""
|
|
|
|
code: str
|
|
|
|
|
|
Health = Literal["ok", "degraded", "down"]
|
|
|
|
|
|
class NodeStatusPublic(BaseModel):
|
|
"""Whether a node loaded, and how its connection is doing."""
|
|
|
|
id: str
|
|
status: str = "active"
|
|
error: str | None = None
|
|
health: Health = "ok"
|
|
health_detail: str | None = None
|
|
|
|
|
|
class MessageValue(BaseModel):
|
|
"""The last payload seen on a message."""
|
|
|
|
value: Any = None
|
|
ts: float | None = None
|
|
|
|
|
|
class HistoryPoint(BaseModel):
|
|
"""One numeric value a message carried, and when."""
|
|
|
|
ts: float
|
|
value: float
|
|
|
|
|
|
class MessageHistory(BaseModel):
|
|
"""A message's recent numeric values, oldest first.
|
|
|
|
Only numbers are recorded, so ``numeric`` tells the panel whether an empty
|
|
series means "nothing plottable here" or "nothing has arrived yet".
|
|
"""
|
|
|
|
message: str
|
|
numeric: bool = False
|
|
points: list[HistoryPoint] = Field(default_factory=list)
|
|
|
|
|
|
class FlowSummary(BaseModel):
|
|
name: str
|
|
title: str = ""
|
|
node_count: int = 0
|
|
error_count: int = 0
|
|
has_draft: bool = False
|
|
enabled: bool = True
|
|
paused: bool = False
|
|
# Its background tasks kept crashing, so the engine stopped restarting them.
|
|
quarantined: bool = False
|
|
|
|
|
|
class FlowsPublic(BaseModel):
|
|
data: list[FlowSummary]
|
|
count: int
|
|
|
|
|
|
class LibraryNode(BaseModel):
|
|
"""A node source shared across flows, and who is using it."""
|
|
|
|
name: str
|
|
used_by: list[str] = Field(default_factory=list)
|
|
|
|
|
|
class FlowStatePublic(BaseModel):
|
|
values: dict[str, MessageValue] = Field(default_factory=dict)
|
|
nodes: list[NodeStatusPublic] = Field(default_factory=list)
|
|
|
|
|
|
class ModulePackage(BaseModel):
|
|
"""One package installed in the venv node code runs on."""
|
|
|
|
name: str
|
|
version: str
|
|
|
|
|
|
class ModulesInfo(BaseModel):
|
|
"""The venv node code imports from, and the manifest that describes it."""
|
|
|
|
python_version: str = ""
|
|
venv_path: str = ""
|
|
requirements: str = ""
|
|
packages: list[ModulePackage] = Field(default_factory=list)
|
|
#: Whether what is installed matches the manifest.
|
|
applied: bool = False
|
|
|
|
|
|
class ApplyRequest(BaseModel):
|
|
"""A pip manifest, one requirement per line."""
|
|
|
|
requirements: str = ""
|
|
|
|
|
|
class ApplyResult(BaseModel):
|
|
ok: bool
|
|
output: str = ""
|
|
|
|
|
|
class BrainNode(BaseModel):
|
|
"""One neuron: a thing the engine talks to, or a node that only computes.
|
|
|
|
Nodes of the same type pointing at the same outside thing — one broker
|
|
topic, one URL, one bucket — are a single entry here, whichever flows they
|
|
sit in. ``members`` are the ``flow.node_id`` names behind it, which is also
|
|
what the live events are keyed by.
|
|
"""
|
|
|
|
id: str
|
|
label: str
|
|
kind: str
|
|
members: list[str] = Field(default_factory=list)
|
|
flows: list[str] = Field(default_factory=list)
|
|
issue: str | None = Field(
|
|
default=None,
|
|
description=(
|
|
"Why this neuron cannot run, if validation found something. A "
|
|
"failure the engine hits while running arrives over the socket "
|
|
"instead; this is the part that is already true before anything "
|
|
"fires, and so has to travel with the graph."
|
|
),
|
|
)
|
|
|
|
|
|
class BrainEdge(BaseModel):
|
|
"""Messages carrying values from one neuron to another."""
|
|
|
|
source: str
|
|
target: str
|
|
messages: list[str] = Field(default_factory=list)
|
|
|
|
|
|
class BrainGraph(BaseModel):
|
|
"""Every published flow at once, merged on what its nodes talk to."""
|
|
|
|
nodes: list[BrainNode] = Field(default_factory=list)
|
|
edges: list[BrainEdge] = Field(default_factory=list)
|
|
|
|
|
|
class NodeTypeInfo(BaseModel):
|
|
"""A node type the editor can offer, with its parameter schema."""
|
|
|
|
type: str
|
|
title: str
|
|
description: str
|
|
params_schema: dict[str, Any] = Field(default_factory=dict)
|
|
has_source: bool = False
|
|
#: Whether this type takes settings beyond the ones its schema declares.
|
|
#: A function node's params are its author's to name, and reach `process`
|
|
#: as whatever they put there.
|
|
free_params: bool = False
|
|
#: The package a connector came from; empty for the built-in types.
|
|
plugin: str | None = None
|