teleo-infrastructure/scripts/kb_rich_proposal_apply_packet.py

#!/usr/bin/env python3
"""Generate a guarded production apply packet for a mapped rich KB plan.

This is a packet builder, not an executor. It turns the reviewed/mapped rich
proposal creation plan into reproducible SQL files:

* preflight SQL: proposal status, required existing claim IDs, generated-row
  absence, and expected counts;
* rollback rehearsal SQL: the write transaction with a final ROLLBACK;
* optional commit SQL: the same transaction with COMMIT, for separately
  authorized execution only;
* postflight SQL: exact generated-row count/readback;
* rollback-delete SQL: exact reverse deletes for the generated rows.

The packet intentionally does not mark the original rich proposals as applied.
The mapped subset is partial while non-claim targets remain unresolved; marking
the original proposals applied would overstate DB state.
"""

from __future__ import annotations

import argparse
import json
import sys
from pathlib import Path
from typing import Any

HERE = Path(__file__).resolve().parent
sys.path.insert(0, str(HERE))

import kb_rich_proposal_creation_plan as creation_plan  # noqa: E402


def _uuid_values(values: list[str], *, column_name: str = "id") -> str:
    if not values:
        return f"(select null::uuid as {column_name} where false)"
    rows = ",\n    ".join(f"('{value}'::uuid)" for value in values)
    return f"(values\n    {rows}\n  ) as v({column_name})"


def _edge_values(rows: list[dict[str, Any]]) -> str:
    if not rows:
        return "(select null::uuid as from_claim, null::uuid as to_claim, null::edge_type as edge_type where false)"
    values = ",\n    ".join(
        f"('{row['from_claim']}'::uuid, '{row['to_claim']}'::uuid, '{row['edge_type']}'::edge_type)"
        for row in rows
    )
    return f"(values\n    {values}\n  ) as v(from_claim, to_claim, edge_type)"


def _evidence_values(rows: list[dict[str, Any]]) -> str:
    if not rows:
        return "(select null::uuid as claim_id, null::uuid as source_id, null::evidence_role as role where false)"
    values = ",\n    ".join(
        f"('{row['claim_id']}'::uuid, '{row['source_id']}'::uuid, '{row['role']}'::evidence_role)"
        for row in rows
    )
    return f"(values\n    {values}\n  ) as v(claim_id, source_id, role)"


def load_creation_plans(path: Path) -> list[dict[str, Any]]:
    data = json.loads(path.read_text(encoding="utf-8"))
    plans = data.get("creation_plans") if isinstance(data, dict) else None
    if not isinstance(plans, list):
        raise SystemExit(f"{path} does not contain creation_plans")
    return plans


def collect_rows(plans: list[dict[str, Any]]) -> dict[str, list[dict[str, Any]]]:
    rows = {"reasoning_tools": [], "claims": [], "sources": [], "claim_evidence": [], "claim_edges": []}
    for plan in plans:
        planned = plan.get("planned_rows") if isinstance(plan.get("planned_rows"), dict) else {}
        for key in rows:
            value = planned.get(key)
            if isinstance(value, list):
                rows[key].extend(row for row in value if isinstance(row, dict))
    return rows


def collect_required_existing_claims(rows: dict[str, list[dict[str, Any]]]) -> list[dict[str, str]]:
    generated_claim_ids = {row["id"] for row in rows["claims"]}
    required: dict[str, str] = {}
    for edge in rows["claim_edges"]:
        for side in ("from_claim", "to_claim"):
            claim_id = edge.get(side)
            if claim_id and claim_id not in generated_claim_ids:
                required.setdefault(str(claim_id), f"claim_edges.{side}")
    for evidence in rows["claim_evidence"]:
        claim_id = evidence.get("claim_id")
        if claim_id and claim_id not in generated_claim_ids:
            required.setdefault(str(claim_id), "claim_evidence.claim_id")
    return [{"id": claim_id, "reason": reason} for claim_id, reason in sorted(required.items())]


def build_generated_counts_sql(rows: dict[str, list[dict[str, Any]]]) -> str:
    reasoning_tool_ids = [row["id"] for row in rows["reasoning_tools"]]
    claim_ids = [row["id"] for row in rows["claims"]]
    source_ids = [row["id"] for row in rows["sources"]]
    return f"""select
  (select count(*) from public.reasoning_tools where id in (select id from {_uuid_values(reasoning_tool_ids)})) as generated_reasoning_tool_rows,
  (select count(*) from public.claims where id in (select id from {_uuid_values(claim_ids)})) as generated_claim_rows,
  (select count(*) from public.sources where id in (select id from {_uuid_values(source_ids)})) as generated_source_rows,
  (select count(*) from public.claim_edges e join {_edge_values(rows['claim_edges'])} using (from_claim, to_claim, edge_type)) as generated_edge_rows,
  (select count(*) from public.claim_evidence ce join {_evidence_values(rows['claim_evidence'])} using (claim_id, source_id, role)) as generated_evidence_rows;
"""


def build_preflight_sql(plans: list[dict[str, Any]], rows: dict[str, list[dict[str, Any]]]) -> str:
    proposal_ids = [str(plan.get("proposal_id")) for plan in plans if plan.get("proposal_id")]
    required_claims = collect_required_existing_claims(rows)
    required_values = (
        ",\n    ".join(f"('{item['id']}'::uuid, {creation_plan._sql_literal(item['reason'])})" for item in required_claims)
        or "(null::uuid, null::text)"
    )
    expected = {
        "reasoning_tools": len(rows["reasoning_tools"]),
        "claims": len(rows["claims"]),
        "sources": len(rows["sources"]),
        "claim_edges": len(rows["claim_edges"]),
        "claim_evidence": len(rows["claim_evidence"]),
    }
    return f"""\\set ON_ERROR_STOP on
-- Preflight for mapped rich proposal apply packet. Read-only.

select id::text, status, proposal_type, reviewed_by_handle, reviewed_at
from kb_stage.kb_proposals
where id in (select id from {_uuid_values(proposal_ids)})
order by id;

with required(id, reason) as (
  values
    {required_values}
)
select 'missing_required_existing_claims' as check_name, id::text, reason
from required
where id is not null
  and not exists (select 1 from public.claims where public.claims.id = required.id)
order by id;

-- Expected generated rows after authorized commit:
select {expected['reasoning_tools']}::int as expected_reasoning_tools,
       {expected['claims']}::int as expected_claims,
       {expected['sources']}::int as expected_sources,
       {expected['claim_edges']}::int as expected_claim_edges,
       {expected['claim_evidence']}::int as expected_claim_evidence;

-- Must be all zero before production apply.
{build_generated_counts_sql(rows)}"""


def build_write_sql(plans: list[dict[str, Any]], *, commit: bool) -> str:
    sql = "\n\n".join(plan.get("rollback_rehearsal_sql", "") for plan in plans)
    terminator = "commit;" if commit else "rollback;"
    return sql.replace("rollback;", terminator)


def build_postflight_sql(rows: dict[str, list[dict[str, Any]]]) -> str:
    reasoning_tool_ids = [row["id"] for row in rows["reasoning_tools"]]
    claim_ids = [row["id"] for row in rows["claims"]]
    source_ids = [row["id"] for row in rows["sources"]]
    return f"""\\set ON_ERROR_STOP on
-- Postflight row-level readback for mapped rich proposal apply packet.

{build_generated_counts_sql(rows)}

select id::text, agent_id::text, name, category, left(description, 500) as description
from public.reasoning_tools
where id in (select id from {_uuid_values(reasoning_tool_ids)})
order by id;

select id::text, type, confidence, left(text, 220) as text
from public.claims
where id in (select id from {_uuid_values(claim_ids)})
order by id;

select id::text, source_type, left(coalesce(excerpt, ''), 220) as excerpt
from public.sources
where id in (select id from {_uuid_values(source_ids)})
order by id;

select e.from_claim::text, e.to_claim::text, e.edge_type::text
from public.claim_edges e
join {_edge_values(rows['claim_edges'])} using (from_claim, to_claim, edge_type)
order by e.from_claim, e.to_claim, e.edge_type;

select ce.claim_id::text, ce.source_id::text, ce.role::text
from public.claim_evidence ce
join {_evidence_values(rows['claim_evidence'])} using (claim_id, source_id, role)
order by ce.claim_id, ce.source_id, ce.role;

select id::text, superseded_by::text
from public.claims
where superseded_by in (select id from {_uuid_values(claim_ids)})
order by id;
"""


def build_delete_rollback_sql(rows: dict[str, list[dict[str, Any]]]) -> str:
    reasoning_tool_ids = [row["id"] for row in rows["reasoning_tools"]]
    claim_ids = [row["id"] for row in rows["claims"]]
    source_ids = [row["id"] for row in rows["sources"]]
    return f"""\\set ON_ERROR_STOP on
-- Emergency rollback for the mapped generated rows only.
-- Run only before any later production data depends on these generated rows.
begin;

delete from public.claim_evidence ce
using {_evidence_values(rows['claim_evidence'])}
where ce.claim_id = v.claim_id and ce.source_id = v.source_id and ce.role = v.role;

delete from public.claim_edges e
using {_edge_values(rows['claim_edges'])}
where e.from_claim = v.from_claim and e.to_claim = v.to_claim and e.edge_type = v.edge_type;

update public.claims
set superseded_by = null,
    updated_at = now()
where superseded_by in (select id from {_uuid_values(claim_ids)});

delete from public.sources
where id in (select id from {_uuid_values(source_ids)});

delete from public.claims
where id in (select id from {_uuid_values(claim_ids)});

delete from public.reasoning_tools
where id in (select id from {_uuid_values(reasoning_tool_ids)});

commit;
"""


def build_packet(plan_path: Path, *, emit_commit_sql: bool) -> dict[str, Any]:
    plans = load_creation_plans(plan_path)
    rows = collect_rows(plans)
    return {
        "packet_version": 1,
        "plan_path": str(plan_path),
        "proposal_ids": [plan.get("proposal_id") for plan in plans],
        "claim_ceiling": (
            "Production apply packet for mapped supported subset only; original rich proposals are not marked applied "
            "unless the packet fully covers the approved reasoning-tool/claim/source contract."
        ),
        "row_counts": {key: len(value) for key, value in rows.items()},
        "required_existing_claims": collect_required_existing_claims(rows),
        "remaining_blocked_fragments": [
            fragment
            for plan in plans
            for fragment in plan.get("blocked_fragments", [])
            if isinstance(fragment, dict)
        ],
        "unresolved_design_decisions": [
            item
            for plan in plans
            for item in plan.get("unresolved_design_decisions", [])
            if isinstance(item, dict)
        ],
        "marks_original_proposals_applied": False,
        "sql": {
            "preflight": build_preflight_sql(plans, rows),
            "apply_rollback_rehearsal": build_write_sql(plans, commit=False),
            "apply_commit": build_write_sql(plans, commit=True) if emit_commit_sql else None,
            "postflight": build_postflight_sql(rows),
            "delete_rollback": build_delete_rollback_sql(rows),
        },
    }


def write_packet_files(packet: dict[str, Any], output_dir: Path) -> None:
    output_dir.mkdir(parents=True, exist_ok=True)
    sql = packet["sql"]
    (output_dir / "production-preflight.sql").write_text(sql["preflight"], encoding="utf-8")
    (output_dir / "production-apply-rollback-rehearsal.sql").write_text(
        sql["apply_rollback_rehearsal"], encoding="utf-8"
    )
    if sql["apply_commit"]:
        (output_dir / "production-apply-authorized-commit.sql").write_text(sql["apply_commit"], encoding="utf-8")
    (output_dir / "production-postflight.sql").write_text(sql["postflight"], encoding="utf-8")
    (output_dir / "production-delete-rollback.sql").write_text(sql["delete_rollback"], encoding="utf-8")

    summary = {key: value for key, value in packet.items() if key != "sql"}
    (output_dir / "production-apply-packet.json").write_text(json.dumps(summary, indent=2, sort_keys=True), encoding="utf-8")


def parse_args(argv: list[str]) -> argparse.Namespace:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--plan-json", required=True, type=Path, help="mapped rich proposal creation plan JSON")
    parser.add_argument("--output-dir", type=Path, help="directory to write packet files")
    parser.add_argument("--emit-commit-sql", action="store_true", help="also write the authorized COMMIT SQL file")
    return parser.parse_args(argv)


def main(argv: list[str] | None = None) -> int:
    args = parse_args(sys.argv[1:] if argv is None else argv)
    packet = build_packet(args.plan_json, emit_commit_sql=args.emit_commit_sql)
    if args.output_dir:
        write_packet_files(packet, args.output_dir)
    print(json.dumps({key: value for key, value in packet.items() if key != "sql"}, indent=2, sort_keys=True))
    return 0


if __name__ == "__main__":
    raise SystemExit(main())