Transformer la sortie d’un agent en registre d’actions vérifié

python -c "from pathlib import Path; import hashlib; print(hashlib.sha256(Path('notes.txt').read_bytes()).hexdigest())"

openai-agents==0.24.0
pydantic==2.14.1

python -m pip install -r recipe-requirements.txt
mkdir candidate

python action_register_recipe.py produce --source-id OWNED-ID --source notes.txt --candidate candidate/actions.json --model YOUR-STRUCTURED-OUTPUT-MODEL

{
  "approved": true,
  "run_id": "COPY-RUN-ID",
  "source_id": "OWNED-ID",
  "source_sha256": "COPY-SOURCE-SHA256",
  "payload_sha256": "COPY-PAYLOAD-SHA256",
  "reviewer": "YOUR-REVIEWER-ID",
  "review_note": "Describe the source, task, owner, date, quotation and omission checks actually performed."
}

python action_register_recipe.py consume --source-id OWNED-ID --source notes.txt --candidate candidate/actions.json --approval approval.json --out private-output

python -c "from pathlib import Path; import hashlib,json,sys; report=Path(sys.argv[1]); receipt=json.loads(Path(sys.argv[2]).read_text(encoding='utf-8')); assert hashlib.sha256(report.read_bytes()).hexdigest()==receipt['report_sha256']; print('report hash matches receipt')" PATH-PRINTED-FOR-REPORT PATH-PRINTED-FOR-RECEIPT

python -c "import json; from pathlib import Path; p=json.loads(Path('candidate/actions.json').read_text(encoding='utf-8')); p['actions'][0].pop('evidence_quote'); Path('candidate/SYNTHETIC-malformed.json').write_text(json.dumps(p), encoding='utf-8')"
python action_register_recipe.py consume --source-id OWNED-ID --source notes.txt --candidate candidate/SYNTHETIC-malformed.json --approval approval.json --out synthetic-rejection-output

"""Private, bounded recipe. No model call occurs unless `produce` is explicitly run."""

import argparse
import hashlib
import json
import uuid
from datetime import date
from pathlib import Path
from typing import Literal

from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr, ValidationError


class StrictModel(BaseModel):
    model_config = ConfigDict(extra="forbid", strict=True)


class Action(StrictModel):
    action_text: StrictStr
    evidence_quote: StrictStr
    line_start: StrictInt
    line_end: StrictInt
    owner: StrictStr | None
    due_date: StrictStr | None
    evidence_status: Literal["complete", "needs_review"]


class Extraction(StrictModel):
    schema_version: Literal["action-register/v1"]
    status: Literal["ready", "partial", "blocked"]
    source_id: StrictStr
    source_sha256: StrictStr
    actions: list[Action]
    gap_note: StrictStr | None


def digest(data: bytes) -> str:
    return hashlib.sha256(data).hexdigest()


def canonical(payload: Extraction) -> bytes:
    return json.dumps(payload.model_dump(mode="json"), sort_keys=True, ensure_ascii=False, separators=(",", ":")).encode("utf-8")


def check(payload: Extraction, source_id: str, source: bytes) -> None:
    if payload.source_id != source_id or payload.source_sha256 != digest(source):
        raise ValueError("source identity or revision mismatch")
    lines = source.decode("utf-8").splitlines()
    if payload.status == "ready" and (not payload.actions or payload.gap_note is not None):
        raise ValueError("ready requires actions and no gap")
    if payload.status != "ready":
        raise ValueError("partial or blocked result cannot reach consumer")
    for index, item in enumerate(payload.actions, 1):
        if item.evidence_status != "complete":
            raise ValueError(f"action {index}: evidence needs review")
        if not item.action_text.strip() or not item.evidence_quote.strip():
            raise ValueError(f"action {index}: empty task or evidence")
        if not 1 <= item.line_start <= item.line_end <= len(lines):
            raise ValueError(f"action {index}: invalid source line range")
        segment = "\n".join(lines[item.line_start - 1:item.line_end])
        if item.evidence_quote not in segment:
            raise ValueError(f"action {index}: quotation absent from source span")
        if item.owner is not None and not item.owner.strip():
            raise ValueError(f"action {index}: blank owner")
        if item.due_date is not None:
            try:
                if date.fromisoformat(item.due_date).isoformat() != item.due_date:
                    raise ValueError()
            except ValueError as exc:
                raise ValueError(f"action {index}: due date must be YYYY-MM-DD") from exc


def report(payload: Extraction) -> str:
    """Application consumer: a triage register grouped by missing ownership/date."""
    groups = [
        ("Assigned with dates", lambda x: x.owner is not None and x.due_date is not None),
        ("Needs an owner", lambda x: x.owner is None),
        ("Needs a date", lambda x: x.owner is not None and x.due_date is None),
    ]
    rows = ["# Action register for " + payload.source_id, "", "Review artifact; source meaning was approved separately.", ""]
    for heading, predicate in groups:
        rows += ["## " + heading, ""]
        matches = [(n, a) for n, a in enumerate(payload.actions, 1) if predicate(a)]
        for number, action in matches:
            rows += [f"{number}. {action.action_text}", f"   Owner: {action.owner or 'Unspecified'}; due: {action.due_date or 'Unspecified'}", f"   Source lines {action.line_start}-{action.line_end}: {action.evidence_quote}", ""]
        if not matches:
            rows += ["None.", ""]
    return "\n".join(rows)


def load_payload(path: Path) -> Extraction:
    return Extraction.model_validate_json(path.read_bytes(), strict=True)


def consume(source_id: str, source_path: Path, payload_path: Path, approval_path: Path, out_dir: Path) -> tuple[Path, Path]:
    source = source_path.read_bytes()
    payload = load_payload(payload_path)
    check(payload, source_id, source)
    run = json.loads(payload_path.with_suffix(".run.json").read_text(encoding="utf-8"))
    payload_hash = digest(canonical(payload))
    if run.get("source_id") != source_id or run.get("source_sha256") != digest(source) or run.get("payload_sha256") != payload_hash or run.get("last_agent") != "Owned-source action extractor" or not str(run.get("run_id", "")).strip():
        raise ValueError("producer receipt does not match accepted candidate")
    approval = json.loads(approval_path.read_text(encoding="utf-8"))
    if (type(approval) is not dict
            or set(approval) != {"approved", "run_id", "source_id", "source_sha256", "payload_sha256", "reviewer", "review_note"}
            or approval["approved"] is not True
            or any(type(approval[key]) is not str for key in ("run_id", "source_id", "source_sha256", "payload_sha256", "reviewer", "review_note"))
            or not approval["reviewer"].strip() or not approval["review_note"].strip()
            or approval["run_id"] != run["run_id"]
            or approval["source_id"] != source_id
            or approval["source_sha256"] != digest(source)
            or approval["payload_sha256"] != payload_hash):
        raise ValueError("human source/meaning approval must bind exact source and payload hashes")
    body = report(payload).encode("utf-8")
    stem = "action-register-" + payload_hash[:16]
    out_dir.mkdir(parents=True, exist_ok=True)
    target = out_dir / (stem + ".md")
    receipt = out_dir / (stem + ".receipt.json")
    record = {"run_id": run["run_id"], "source_id": source_id, "source_sha256": digest(source), "payload_sha256": payload_hash, "report_sha256": digest(body), "reviewer": approval["reviewer"], "operation": "local action-triage register"}
    encoded = (json.dumps(record, indent=2) + "\n").encode("utf-8")
    for path, data in [(target, body), (receipt, encoded)]:
        if path.exists():
            if path.read_bytes() != data:
                raise ValueError(f"uncertain prior output differs: {path}; inspect before retry")
        else:
            with path.open("xb") as handle:
                handle.write(data)
        if path.read_bytes() != data:
            raise IOError(f"readback failed: {path}")
    return target, receipt


def produce(source_id: str, source_path: Path, candidate_path: Path, model: str) -> None:
    from agents import Agent, Runner

    source = source_path.read_bytes()
    source_text = source.decode("utf-8")
    if not source_text.strip() or candidate_path.exists() or not candidate_path.parent.is_dir():
        raise ValueError("source must contain text; candidate must be new and its parent directory must already exist")
    run_id = str(uuid.uuid4())
    agent = Agent(
        name="Owned-source action extractor",
        model=model,
        instructions=("Extract only explicit action commitments from the supplied numbered source. "
                      "Return action-register/v1. Copy an exact quote with matching 1-based line span. "
                      "Use null for an unstated owner or due date; never infer them. "
                      "Use partial and needs_review for ambiguous evidence; blocked for unusable input. "
                      "Do not use tools or hand off."),
        output_type=Extraction,
    )
    numbered = "\n".join(f"{n}: {line}" for n, line in enumerate(source_text.splitlines(), 1))
    try:
        result = Runner.run_sync(agent, f"Source ID: {source_id}\nSHA-256: {digest(source)}\nNumbered source:\n{numbered}")
        if result.interruptions or result.last_agent is not agent or not isinstance(result.final_output, Extraction):
            raise ValueError("run interrupted, unfinished, or finished by unexpected agent; this CLI does not persist resumable RunState, so do not resume from its failure receipt")
        output = result.final_output
        if output.source_id != source_id or output.source_sha256 != digest(source):
            raise ValueError("producer returned wrong source identity")
        candidate = canonical(output)
        with candidate_path.open("xb") as handle:
            handle.write(candidate)  # Candidate only; consumer still requires review.
        receipt = {"run_id": run_id, "source_id": source_id, "source_sha256": digest(source), "payload_sha256": digest(candidate), "last_agent": result.last_agent.name, "model": model}
        with candidate_path.with_suffix(".run.json").open("x", encoding="utf-8") as handle:
            handle.write(json.dumps(receipt, indent=2) + "\n")
    except Exception as exc:
        failure = {"run_id": run_id, "source_id": source_id, "source_sha256": digest(source), "error_type": type(exc).__name__, "error": str(exc), "state": "unknown_or_blocked; inspect run and destination before retry"}
        with candidate_path.with_name(candidate_path.stem + "." + run_id + ".failure.json").open("x", encoding="utf-8") as handle:
            handle.write(json.dumps(failure, indent=2) + "\n")
        raise


def main() -> None:
    parser = argparse.ArgumentParser()
    sub = parser.add_subparsers(dest="command", required=True)
    for name in ("produce", "consume"):
        p = sub.add_parser(name)
        p.add_argument("--source-id", required=True)
        p.add_argument("--source", type=Path, required=True)
        if name == "produce":
            p.add_argument("--candidate", type=Path, required=True)
            p.add_argument("--model", required=True)
        else:
            p.add_argument("--candidate", type=Path, required=True)
            p.add_argument("--approval", type=Path, required=True)
            p.add_argument("--out", type=Path, required=True)
    args = parser.parse_args()
    if args.command == "produce":
        produce(args.source_id, args.source, args.candidate, args.model)
    else:
        print(*consume(args.source_id, args.source, args.candidate, args.approval, args.out), sep="\n")


if __name__ == "__main__":
    main()