src/slop_farmer/app/workflow.py

from __future__ import annotations

import json
from datetime import UTC, datetime

from slop_farmer.app.pipeline import run_pipeline
from slop_farmer.config import (
    AnalysisOptions,
    DashboardDataOptions,
    FullPipelineOptions,
    MarkdownReportOptions,
    PipelineOptions,
)
from slop_farmer.reports.analysis import render_markdown_report, run_analysis
from slop_farmer.reports.dashboard import run_dashboard_data


def run_full_pipeline(options: FullPipelineOptions) -> str:
    repo_anchor = options.repo.name
    base_dir = options.workspace_root.resolve() / repo_anchor
    data_dir = base_dir / "data"
    dashboard_dir = base_dir / "web" / "public" / "data"

    snapshot_dir = run_pipeline(
        PipelineOptions(
            repo=options.repo,
            output_dir=data_dir,
            since=None,
            resume=True,
            http_timeout=180,
            http_max_retries=5,
            max_issues=options.max_issues,
            max_prs=options.max_prs,
            max_issue_comments=None,
            max_reviews_per_pr=None,
            max_review_comments_per_pr=None,
            fetch_timeline=options.fetch_timeline,
            publish=True,
            hf_repo_id=options.dataset,
            private_hf_repo=options.private_hf_repo,
            new_contributor_report=True,
            new_contributor_window_days=options.new_contributor_window_days,
            new_contributor_max_authors=0,
            issue_max_age_days=options.issue_max_age_days,
            pr_max_age_days=options.pr_max_age_days,
        )
    )

    analysis_path = run_analysis(
        AnalysisOptions(
            snapshot_dir=snapshot_dir,
            output_dir=data_dir,
            output=None,
            hf_repo_id=None,
            hf_revision=None,
            hf_materialize_dir=None,
            ranking_backend=options.ranking_backend,
            model=options.model,
            max_clusters=options.max_clusters,
            open_prs_only=options.open_prs_only,
        )
    )
    markdown_path = render_markdown_report(
        MarkdownReportOptions(
            input=analysis_path,
            output=None,
            snapshot_dir=snapshot_dir,
        )
    )
    dashboard_output = run_dashboard_data(
        DashboardDataOptions(
            snapshot_dir=snapshot_dir,
            output_dir=dashboard_dir,
            analysis_input=analysis_path,
            contributors_input=snapshot_dir / "new-contributors-report.json",
            pr_scope_input=snapshot_dir / "pr-scope-clusters.json",
            window_days=options.dashboard_window_days,
        )
    )
    payload = {
        "repo": options.repo.slug,
        "dataset": options.dataset,
        "workspace": str(base_dir),
        "snapshot_dir": str(snapshot_dir),
        "analysis_report_json": str(analysis_path),
        "analysis_report_markdown": str(markdown_path),
        "dashboard_output_dir": str(dashboard_output),
        "generated_at": datetime.now(tz=UTC)
        .replace(microsecond=0)
        .isoformat()
        .replace("+00:00", "Z"),
    }
    return json.dumps(payload, indent=2)