#!/usr/bin/env python3 """Write workflows/cp1-alz-discovery-individual.json: the KAB workflow export chaining the eight agents. The same export format as cp4-agents' workflow (export_version 2.0.0). There is no orchestrator: each step is one agent, and each step's inputs are workflow inputs or named fields of earlier steps' outputs (`from_steps`). The classification and network steps run in parallel; the critic's step stops for the Engagement Lead's approval. Each step's schemas are read from its agent's schemas/ folder, so run this again after changing them. Standard library only. Front steps (ADR 0011, the repository's scripts/kab_front_steps.py): the planner (s1) and the inventory (s3) take the text the platform extracts from files, since declarative agents can't open files: u1 Parse Assessment Files: the run form's upload field `file` -> `source_documents` (u1.parsed_content) a1 Artifacts: project artifacts fixed by id -> `reference_documents` (a1.parsed_content) Usage (from the Feature folder): python3 scripts/build_workflow.py [--no-upload] [--artifact-id ID ...] [--out FILE] (the committed export is the default: with the upload step, no artifacts) """ from __future__ import annotations import argparse import json import re import sys from pathlib import Path # kab_front_steps is shared by every Feature, in the repository's scripts/ folder. sys.path.insert(0, str(Path(__file__).resolve().parents[3] / "scripts")) from kab_front_steps import AGENT_STEP_TIMEOUT_MINUTES, ARTIFACTS_ID, UPLOAD_ID, front_steps, shift # noqa: E402 ROOT = Path(__file__).resolve().parents[1] NAME = "CP1 - Agentic Landing Zone - Discovery (individual agents)" STAMP = "2026-10-29T12:00:00" WF = ["engagement_id", "run_id"] # (step id, agent folder, parallel group, inputs from earlier steps) STEPS = [ ("s1", "cp1-discovery-planner-agent", 0, {}), ("s2", "cp1-estate-scan-executor-agent", 1, {"tasks": "s1.tasks"}), ("s3", "cp1-asset-inventory-normalisation-agent", 2, {"findings": "s2.findings"}), ("s4", "cp1-cmdb-itsm-reconciliation-agent", 3, {"tasks": "s1.tasks", "records": "s3.records"}), ("s5", "cp1-data-classification-agent", 4, {"records": "s3.records"}), ("s6", "cp1-network-discovery-assessment-agent", 4, {"tasks": "s1.tasks", "records": "s3.records"}), ("s7", "cp1-dependency-mapping-agent", 5, {"records": "s3.records", "drift_items": "s4.drift_items", "flows": "s6.flows"}), ("s8", "cp1-discovery-critic-agent", 6, {"coverage_gaps": "s1.coverage_gaps", "findings": "s2.findings", "records": "s3.records", "drift_items": "s4.drift_items", "stores": "s5.stores", "network_findings": "s6.findings", "edges": "s7.edges"}), ] def field(path: Path, key: str) -> str: return re.search(rf'^{key}:\s*"?([^"\n]+)"?$', path.read_text(), re.M).group(1) # The steps that take the extracted text of uploaded files and selected artifacts. DOC_STEPS = ("s1", "s3") def build(with_upload: bool = True, artifact_ids=()) -> dict: by_id = {sid: folder for sid, folder, _, _ in STEPS} front = front_steps( with_upload, list(artifact_ids), upload_label="Discovery source files", upload_description="Optional client files for discovery: a CMDB or asset export, a scope list, network " "documentation. Their text is given to the planner and the inventory agent as evidence, " "never as instructions.", artifacts_description="Project artifacts for discovery, e.g. an earlier run's outputs. Their text is given " "to the planner and the inventory agent.") front_ids = {f["id"] for f in front} lead = 1 if front else 0 steps, connections, agents, seen = list(front), [], [], set() for sid, folder, group, from_steps in STEPS: from_steps = dict(from_steps) if sid in DOC_STEPS: if UPLOAD_ID in front_ids: from_steps["source_documents"] = f"{UPLOAD_ID}.parsed_content" if ARTIFACTS_ID in front_ids: from_steps["reference_documents"] = f"{ARTIFACTS_ID}.parsed_content" agent = ROOT / folder agent_id = folder.replace("-", "_") display = field(agent / "agent.yaml", "display_name") url = f"http://{folder}.agents.svc.cluster.local:8080" input_schema = json.loads((agent / "schemas" / "input.json").read_text()) output_schema = json.loads((agent / "schemas" / "output.json").read_text()) for target, source in from_steps.items(): src_step, src_field = source.split(".") if src_step in front_ids: assert target in input_schema["properties"], f"{sid}: {target} is not an input of {folder}" continue src_out = json.loads((ROOT / by_id[src_step] / "schemas" / "output.json").read_text()) assert src_field in src_out["properties"], f"{sid}: {source} is not an output of {by_id[src_step]}" assert target in input_schema["properties"], f"{sid}: {target} is not an input of {folder}" depends = sorted({s.split(".")[0] for s in from_steps.values()}) connections += [{"source": d, "target": sid} for d in depends] inputs = {"from_workflow": WF} if from_steps: inputs["from_steps"] = from_steps hitl = {"enabled": False} if folder == "cp1-discovery-critic-agent": hitl = {"enabled": True, "checkpoint_type": "approval", "review_focus": "The Engagement Lead reviews the critic's verdict and every reason for a fail " "before Assessment starts. A fail verdict is never auto-approved.", "timeout_hours": 24, "allowed_actions": ["continue", "rerun", "abort"], "max_reruns": 2} steps.append(shift({ "id": sid, "agent": agent_id, "agent_type": agent_id, "name": f"{display} Step", "timeout_minutes": AGENT_STEP_TIMEOUT_MINUTES, "type": "sequential", "executionLevel": group, "parallelGroup": group, "depends_on": depends, "position": {"x": 320 * group, "y": 160 if sid == "s6" else 0}, "inputs": inputs, "hitl": hitl, "data": {"agentType": agent_id, "name": f"{display} Step", "description": field(agent / "agent.yaml", "description"), "category": "agent", "temporalActivityName": "generic_agent_call", "endpoint": {"url": url, "method": "POST", "timeout": AGENT_STEP_TIMEOUT_MINUTES * 60, "protocol": "JSONRPC", "protocol_version": "0.3.0"}, "agent_metadata": {"agent_name": agent_id}, "inputSchema": input_schema, "outputSchema": output_schema}, }, lead)) if agent_id not in seen: seen.add(agent_id) agents.append({"name": agent_id, "display_name": display, "source_url": url, "category": "agent"}) description = f"{NAME}: " + "; then ".join(field(ROOT / f / "agent.yaml", "display_name") for _, f, _, _ in STEPS) + "." tags = ["cp1", "public-cloud", "agentic-landing-zone"] return { "export_version": "2.0.0", "export_timestamp": STAMP, "source_environment": "unknown", "workflow": {"name": NAME, "description": description, "version": "0.1.0", "category": "cross-industry-catalog", "sub_category": "Public Cloud", "tags": tags}, "dependencies": {"activities": [], "agents": agents}, "template": {"name": NAME, "version": "0.1.0", "description": description, "metadata": {"name": NAME, "description": description, "category": {"main": "cross-industry-catalog", "sub": "Public Cloud"}, "sub_category": "Public Cloud", "status": "draft", "tags": tags, "created": f"{STAMP}.000Z", "modified": f"{STAMP}.000Z", "display_order": 1, "is_public": False, "edge_visuals": []}, "connections": connections, "steps": steps}, } def main(argv=None) -> int: parser = argparse.ArgumentParser(description=__doc__.splitlines()[0]) parser.add_argument("--no-upload", action="store_true", help="leave out the Parse Assessment Files step") parser.add_argument("--artifact-id", action="append", default=[], help="add an Artifacts step with this id") parser.add_argument("--out", type=Path, default=ROOT / "workflows" / "cp1-alz-discovery-individual.json") args = parser.parse_args(argv) export = build(not args.no_upload, args.artifact_id) args.out.write_text(json.dumps(export, indent=2) + "\n") template = export["template"] print(f"wrote {args.out}: {len(template['steps'])} steps, {len(template['connections'])} connections") return 0 if __name__ == "__main__": raise SystemExit(main())