GarminHealthLab/backend/routes/analysis.py

"""Analysis routes: trends, recommendations, and the AI coach."""
import json

from flask import Blueprint, Response, request, g, jsonify

from auth import require_auth
from services import analysis as analysis_svc
from services import ai as ai_svc
from services import insights

bp = Blueprint("analysis", __name__)


@bp.route("/trends", methods=["GET"])
@require_auth
def trends():
    metric = request.args.get("metricType", "steps")
    s = request.args.get("startDate")
    e = request.args.get("endDate")
    return jsonify(analysis_svc.get_trends(metric, g.user_id, s, e))


@bp.route("/recommendations", methods=["GET"])
@require_auth
def recommendations():
    return jsonify(analysis_svc.get_recommendations(g.user_id))


@bp.route("/models", methods=["GET"])
@require_auth
def models():
    """Available LLMs and whether each one has credentials configured."""
    return jsonify(ai_svc.list_models())


@bp.route("/ai-recommendations", methods=["GET"])
@require_auth
def ai_recommendations():
    """LLM recommendations. `?model=` picks one; omit it to use the chain.

    Served from cache unless `?refresh=1` or an explicit `model` is given —
    a fresh generation can take minutes against a large reasoning model.

    Always 200: when no model succeeds the rule engine answers instead, and
    meta.source says which produced the result.
    """
    model = request.args.get("model") or None
    days = request.args.get("days", type=int)
    refresh = request.args.get("refresh") in ("1", "true", "yes")
    return jsonify(
        analysis_svc.get_ai_recommendations(g.user_id, model, days, refresh)
    )


def _flag(name):
    return request.args.get(name) in ("1", "true", "yes")


@bp.route("/briefing", methods=["GET"])
@require_auth
def briefing():
    """AI 晨间简报 + 今日运动处方, plus the computed context behind it.

    Answers immediately. When no cached model answer matches the current data
    the rule-based briefing is returned with `meta.pending`, and a generation
    runs in the background — a model round-trip costs minutes, which cannot
    sit in the first paint of the 今日 screen. Poll the same URL to pick up
    the model's version.

    `?wait=1` blocks for the model instead, for a deliberate regenerate.
    """
    return jsonify(analysis_svc.get_briefing(
        g.user_id,
        date=request.args.get("date"),
        model=request.args.get("model") or None,
        refresh=_flag("refresh"),
        wait=_flag("wait"),
    ))


@bp.route("/trend-insight", methods=["GET"])
@require_auth
def trend_insight():
    """Attribution for one metric over a selected span (chart brush)."""
    metric = request.args.get("metric")
    start = request.args.get("startDate")
    end = request.args.get("endDate")
    if not (metric and start and end):
        return jsonify({"error": "缺少 metric / startDate / endDate 参数"}), 400
    if metric not in insights.METRICS:
        return jsonify({
            "error": f"不支持的指标: {metric}",
            "supported": sorted(insights.METRICS),
        }), 400
    return jsonify(analysis_svc.get_trend_insight(
        g.user_id, metric, start, end,
        model=request.args.get("model") or None,
        refresh=_flag("refresh"),
    ))


@bp.route("/copilot", methods=["POST"])
@require_auth
def copilot():
    """Health Copilot, streamed as server-sent events.

    Streaming is about keeping the connection honest as much as about speed:
    the upstream can think for minutes before its first token, and a plain
    JSON request that long is indistinguishable from a hang — to the user, to
    a proxy, and to Gunicorn's worker timeout.
    """
    body = request.get_json(silent=True) or {}
    question = (body.get("question") or "").strip()
    if not question:
        return jsonify({"error": "缺少 question"}), 400

    history = body.get("history")
    history = history if isinstance(history, list) else []
    # Read off `g` here, not inside the generator: the request context is torn
    # down before the first chunk is pulled, and touching g there raises.
    user_id = g.user_id
    date = body.get("date")
    model = body.get("model") or None

    def events():
        for event, data in analysis_svc.copilot_stream(
            user_id, question, history, date, model
        ):
            yield f"event: {event}\ndata: {json.dumps(data, ensure_ascii=False)}\n\n"

    return Response(
        events(),
        mimetype="text/event-stream",
        # X-Accel-Buffering stops nginx-style proxies from holding the stream
        # until it completes, which would undo the point of streaming it.
        headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"},
    )