Files
gcp_solution_architecture_a…/app/workflows/execution_graph.py
Jonathan Boniface 844987587c feat: consult only the pillars a change affects directly (iteration 5 step 3)
A graded question per pillar (not at all, only indirectly, directly) picks
the pillar advisors to consult again on a Revision or a Change request; the
design advisor is told which, and keeps its earlier advice for the rest. As
a yes or no the answer was yes for nearly every pillar of every change.

A completed Execution now writes working.json with each pillar's advice
and checklist review, and a Change request starts from its Baseline's, so
only the pillars a change touches are consulted afresh.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 15:22:57 +01:00

79 lines
2.6 KiB
Python

"""The LangGraph that holds an Execution (ADR-0003).
START -> orchestrator_turn
orchestrator_turn -> specialist_task x N (Send, parallel) -> orchestrator_turn
orchestrator_turn -> await_user (interrupt) -> orchestrator_turn
orchestrator_turn -> finalize -> END
orchestrator_turn -> end_with_warnings -> END
The nodes live in app/nodes/execution_nodes.py; they route with Command and Send, so
only the fixed edges are declared here.
"""
from __future__ import annotations
from collections.abc import Mapping
from pathlib import Path
from typing import Any, cast
from langgraph.graph import END, START, StateGraph
from app.adk.runtime import (
AgentRuntime,
Decider,
RoleSpec,
RunLimiter,
SubmissionReview,
ToolFactory,
)
from app.nodes.execution_nodes import make_execution_nodes
from app.nodes.router import OrchestratorPolicy
from app.recorder import ExecutionRecorder
from app.states.execution_state import ExecutionState
def build_execution_graph(
*,
runtime: AgentRuntime,
roles: Mapping[str, RoleSpec],
recorder: ExecutionRecorder,
output_root: Path,
max_orchestrator_turns: int = 100,
tool_factory: ToolFactory | None = None,
limiter: RunLimiter | None = None,
skill_versions: Mapping[str, str] | None = None,
orchestrator: OrchestratorPolicy | None = None,
submission_review: SubmissionReview | None = None,
confirm_drafts: bool = False,
decider: Decider | None = None,
pillar_threshold: float = 1.5,
) -> StateGraph:
nodes = make_execution_nodes(
runtime=runtime,
roles=roles,
recorder=recorder,
output_root=output_root,
max_orchestrator_turns=max_orchestrator_turns,
tool_factory=tool_factory,
limiter=limiter,
skill_versions=skill_versions,
orchestrator=orchestrator,
submission_review=submission_review,
confirm_drafts=confirm_drafts,
decider=decider,
pillar_threshold=pillar_threshold,
)
graph = StateGraph(ExecutionState)
graph.add_node("orchestrator_turn", cast(Any, nodes.orchestrator_turn))
# Specialist tasks receive their Send payload, not the Execution state.
graph.add_node("specialist_task", cast(Any, nodes.specialist_task))
graph.add_node("await_user", cast(Any, nodes.await_user))
graph.add_node("finalize", cast(Any, nodes.finalize))
graph.add_node("end_with_warnings", cast(Any, nodes.end_with_warnings))
graph.add_edge(START, "orchestrator_turn")
graph.add_edge("specialist_task", "orchestrator_turn")
graph.add_edge("finalize", END)
graph.add_edge("end_with_warnings", END)
return graph