diff --git a/backend/app/api/admin/settings.py b/backend/app/api/admin/settings.py index 2f30e5d..e10cd17 100644 --- a/backend/app/api/admin/settings.py +++ b/backend/app/api/admin/settings.py @@ -1,5 +1,6 @@ from __future__ import annotations +import math from typing import Any from fastapi import APIRouter, Depends, Request @@ -34,6 +35,8 @@ _DEFAULT_RECOMMENDATION: dict[str, Any] = { "pick_mode": "weighted", "temperature": 1.0, "score_weights": dict(_DEFAULT_SCORE_WEIGHTS), + "freshness_half_life_days": 21.0, + "velocity_smooth_days": 2.0, "multipliers": { "ai": 1.0, "non_ai": 1.0, @@ -52,6 +55,15 @@ _DEFAULT_SETTINGS = { "fail_cooldown_ms": 600_000, "strategy": "quality", "quality_samples": 12, + "dedup": { + "enabled": True, + "window_s": 20 * 60, + "max_images": 5000, + "max_authors": 2000, + "strict": False, + "image_penalty": 8.0, + "author_penalty": 2.5, + }, "recommendation": dict(_DEFAULT_RECOMMENDATION), }, "proxy": {"allowlist_domains": []}, @@ -99,6 +111,79 @@ def _as_float(value: Any) -> float | None: return None +def _normalize_dedup(value: Any, *, strict: bool) -> dict[str, Any]: + default = dict(_DEFAULT_SETTINGS["random"]["dedup"]) + if value is None: + return default + if not isinstance(value, dict): + if strict: + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup", status_code=400) + return default + + if strict: + for k in value.keys(): + if str(k) not in default: + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup", status_code=400) + + enabled = default["enabled"] + v = _as_bool(value.get("enabled")) + if v is not None: + enabled = bool(v) + + window_s = int(default["window_s"]) + if "window_s" in value: + try: + n = int(value.get("window_s")) + except Exception as exc: + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup.window_s", status_code=400) from exc + window_s = int(max(0, min(n, 24 * 60 * 60))) + + max_images = int(default["max_images"]) + if "max_images" in value: + try: + n = int(value.get("max_images")) + except Exception as exc: + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup.max_images", status_code=400) from exc + max_images = int(max(1, min(n, 200_000))) + + max_authors = int(default["max_authors"]) + if "max_authors" in value: + try: + n = int(value.get("max_authors")) + except Exception as exc: + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup.max_authors", status_code=400) from exc + max_authors = int(max(1, min(n, 200_000))) + + strict_mode = bool(default["strict"]) + v = _as_bool(value.get("strict")) + if v is not None: + strict_mode = bool(v) + + image_penalty = float(default["image_penalty"]) + if "image_penalty" in value: + v = _as_float(value.get("image_penalty")) + if v is None or not math.isfinite(float(v)): + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup.image_penalty", status_code=400) + image_penalty = float(max(0.0, min(float(v), 1000.0))) + + author_penalty = float(default["author_penalty"]) + if "author_penalty" in value: + v = _as_float(value.get("author_penalty")) + if v is None or not math.isfinite(float(v)): + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Invalid random.dedup.author_penalty", status_code=400) + author_penalty = float(max(0.0, min(float(v), 1000.0))) + + return { + "enabled": bool(enabled), + "window_s": int(window_s), + "max_images": int(max_images), + "max_authors": int(max_authors), + "strict": bool(strict_mode), + "image_penalty": float(image_penalty), + "author_penalty": float(author_penalty), + } + + def _normalize_recommendation(value: Any, *, strict: bool) -> dict[str, Any]: if value is None: return dict(_DEFAULT_RECOMMENDATION) @@ -132,6 +217,34 @@ def _normalize_recommendation(value: Any, *, strict: bool) -> dict[str, Any]: else: temperature = float(max(0.05, min(float(v), 100.0))) + freshness_half_life_default = float(_DEFAULT_RECOMMENDATION["freshness_half_life_days"]) + freshness_half_life_days = freshness_half_life_default + if "freshness_half_life_days" in value: + v = _as_float(value.get("freshness_half_life_days")) + if v is None or not math.isfinite(float(v)): + if strict: + raise ApiError( + code=ErrorCode.BAD_REQUEST, + message="Invalid random.recommendation.freshness_half_life_days", + status_code=400, + ) + else: + freshness_half_life_days = float(max(0.1, min(float(v), 3650.0))) + + velocity_smooth_default = float(_DEFAULT_RECOMMENDATION["velocity_smooth_days"]) + velocity_smooth_days = velocity_smooth_default + if "velocity_smooth_days" in value: + v = _as_float(value.get("velocity_smooth_days")) + if v is None or not math.isfinite(float(v)): + if strict: + raise ApiError( + code=ErrorCode.BAD_REQUEST, + message="Invalid random.recommendation.velocity_smooth_days", + status_code=400, + ) + else: + velocity_smooth_days = float(max(0.0, min(float(v), 3650.0))) + score_weights_default = _DEFAULT_RECOMMENDATION["score_weights"] score_weights_raw = value.get("score_weights") if score_weights_raw is None: @@ -202,6 +315,8 @@ def _normalize_recommendation(value: Any, *, strict: bool) -> dict[str, Any]: "pick_mode": pick_mode, "temperature": temperature, "score_weights": score_weights, + "freshness_half_life_days": float(freshness_half_life_days), + "velocity_smooth_days": float(velocity_smooth_days), "multipliers": multipliers, } @@ -244,8 +359,10 @@ async def get_settings( if k in runtime.random_defaults: random_defaults[k] = runtime.random_defaults[k] random_defaults["recommendation"] = _normalize_recommendation(runtime.random_defaults.get("recommendation"), strict=False) + random_defaults["dedup"] = _normalize_dedup(runtime.random_defaults.get("dedup"), strict=False) else: random_defaults["recommendation"] = _normalize_recommendation(None, strict=False) + random_defaults["dedup"] = _normalize_dedup(None, strict=False) return { "ok": True, @@ -434,6 +551,9 @@ async def update_settings( if "recommendation" in random: defaults["recommendation"] = _normalize_recommendation(random.get("recommendation"), strict=True) + if "dedup" in random: + defaults["dedup"] = _normalize_dedup(random.get("dedup"), strict=True) + if defaults: values = await fetch_runtime_settings(request.app.state.engine) runtime = runtime_config_from_values(values) diff --git a/backend/app/api/public/docs_page.py b/backend/app/api/public/docs_page.py index e20927c..74e1f07 100644 --- a/backend/app/api/public/docs_page.py +++ b/backend/app/api/public/docs_page.py @@ -23,6 +23,11 @@ def _build_docs_html(*, base_url: str) -> str: "img_pixiv_cat": u("/random?pixiv_cat=1"), "img_pixiv_re": u("/random?pixiv_cat=1&pximg_mirror_host=re"), "img_redirect": u("/random?redirect=1"), + "rec_tune": u( + "/random?strategy=quality&rec_pick_mode=weighted&rec_temperature=1" + "&rec_w_freshness=2&rec_fresh_half_life_days=14" + "&rec_w_bookmark_velocity=2&rec_velocity_smooth_days=2" + ), "status": u("/status"), "status_json": u("/status.json"), "wtf": u("/wtf"), @@ -417,6 +422,19 @@ def _build_docs_html(*, base_url: str) -> str: +
+ 推荐策略 URL 覆盖（rec_*）
+ 这些参数仅影响本次请求，不需要登录，也不会修改后台默认配置： + + 示例：{examples["rec_tune"]} +
其它接口：/tags（标签列表）、/authors（作者列表）。
OpenAPI：/openapi.json，Swagger：/api/docs。
diff --git a/backend/app/api/public/random.py b/backend/app/api/public/random.py index 5825cbc..aa3ae92 100644 --- a/backend/app/api/public/random.py +++ b/backend/app/api/public/random.py @@ -37,37 +37,42 @@ _MAX_TAG_FILTERS = 50 _MAX_TAG_OR_TERMS = 20 _MAX_TAG_TOTAL_TERMS = 200 -# Best-effort anti-repeat (process-local): reduce short-term duplicates without extra DB writes. +# Best-effort global de-dup (process-local): reduce short-term duplicates without extra DB writes. _RECENT_LOCK = Lock() -_RECENT_WINDOW_S = 20.0 * 60.0 -_RECENT_MAX_IMAGES = 600 -_RECENT_MAX_AUTHORS = 200 _RECENT_IMAGES: deque[tuple[float, int]] = deque() _RECENT_AUTHORS: deque[tuple[float, int]] = deque() -def _prune_recent(now: float) -> None: - cutoff = float(now) - float(_RECENT_WINDOW_S) +def _prune_recent(now: float, *, window_s: float, max_images: int, max_authors: int) -> None: + cutoff = float(now) - float(window_s) while _RECENT_IMAGES and float(_RECENT_IMAGES[0][0]) < cutoff: _RECENT_IMAGES.popleft() while _RECENT_AUTHORS and float(_RECENT_AUTHORS[0][0]) < cutoff: _RECENT_AUTHORS.popleft() - while len(_RECENT_IMAGES) > int(_RECENT_MAX_IMAGES): + while len(_RECENT_IMAGES) > int(max_images): _RECENT_IMAGES.popleft() - while len(_RECENT_AUTHORS) > int(_RECENT_MAX_AUTHORS): + while len(_RECENT_AUTHORS) > int(max_authors): _RECENT_AUTHORS.popleft() -def _get_recent_sets(now: float) -> tuple[set[int], set[int]]: +def _get_recent_sets(now: float, *, window_s: float, max_images: int, max_authors: int) -> tuple[set[int], set[int]]: with _RECENT_LOCK: - _prune_recent(now) + _prune_recent(now, window_s=float(window_s), max_images=int(max_images), max_authors=int(max_authors)) recent_images = {int(image_id) for _t, image_id in _RECENT_IMAGES} recent_authors = {int(user_id) for _t, user_id in _RECENT_AUTHORS} return recent_images, recent_authors -def _record_recent(*, now: float, image_id: int, user_id: int | None) -> None: +def _record_recent( + *, + now: float, + image_id: int, + user_id: int | None, + window_s: float, + max_images: int, + max_authors: int, +) -> None: try: image_id_i = int(image_id) except Exception: @@ -81,12 +86,26 @@ def _record_recent(*, now: float, image_id: int, user_id: int | None) -> None: user_id_i = None with _RECENT_LOCK: - _prune_recent(now) + _prune_recent(now, window_s=float(window_s), max_images=int(max_images), max_authors=int(max_authors)) _RECENT_IMAGES.append((float(now), int(image_id_i))) if user_id_i is not None and user_id_i > 0: _RECENT_AUTHORS.append((float(now), int(user_id_i))) +def _as_bool(value: Any) -> bool | None: + if isinstance(value, bool): + return value + if isinstance(value, int) and value in (0, 1): + return bool(value) + if isinstance(value, str): + v = value.strip().lower() + if v in {"true", "1", "yes", "y", "on"}: + return True + if v in {"false", "0", "no", "n", "off"}: + return False + return None + + def _as_nonneg_int(value: Any) -> int: if value is None: return 0 @@ -116,6 +135,11 @@ _DEFAULT_RECOMMENDATION: dict[str, Any] = { "pick_mode": "weighted", "temperature": 1.0, "score_weights": dict(_DEFAULT_SCORE_WEIGHTS), + # Newness/trending knobs: + # - freshness_half_life_days: used by the freshness decay term (see scoring). + # - velocity_smooth_days: smoothing for bookmark velocity denominator (age_days + smooth). + "freshness_half_life_days": 21.0, + "velocity_smooth_days": 2.0, "multipliers": { "ai": 1.0, "non_ai": 1.0, @@ -139,6 +163,94 @@ def _as_float(value: Any, *, default: float) -> float: return float(default) +def _parse_recommendation_overrides_from_query(query_params: Any) -> tuple[dict[str, Any], list[str]]: + qp = query_params or {} + used: list[str] = [] + overrides: dict[str, Any] = {} + + def _get_str(name: str) -> str | None: + try: + raw = qp.get(name) + except Exception: + raw = None + if raw is None: + return None + s = str(raw).strip() + if not s: + return None + used.append(name) + return s + + def _get_float(name: str) -> float | None: + try: + raw = qp.get(name) + except Exception: + raw = None + if raw is None: + return None + v = _as_float(raw, default=float("nan")) + if not math.isfinite(float(v)): + raise ApiError(code=ErrorCode.BAD_REQUEST, message=f"Unsupported {name}", status_code=400) + used.append(name) + return float(v) + + # Be strict for rec_* prefixes to avoid silent typos. + try: + keys = list(qp.keys()) + except Exception: + keys = [] + for k in keys: + if not isinstance(k, str): + continue + if k.startswith("rec_w_"): + weight_key = k.removeprefix("rec_w_") + if weight_key not in _DEFAULT_SCORE_WEIGHTS: + raise ApiError(code=ErrorCode.BAD_REQUEST, message=f"Unsupported {k}", status_code=400) + if k.startswith("rec_m_"): + mult_key = k.removeprefix("rec_m_") + if mult_key not in _DEFAULT_RECOMMENDATION["multipliers"]: + raise ApiError(code=ErrorCode.BAD_REQUEST, message=f"Unsupported {k}", status_code=400) + + pick_mode_s = _get_str("rec_pick_mode") + if pick_mode_s is not None: + candidate = pick_mode_s.strip().lower() + if candidate not in {"best", "weighted"}: + raise ApiError(code=ErrorCode.BAD_REQUEST, message="Unsupported rec_pick_mode", status_code=400) + overrides["pick_mode"] = candidate + + temperature_v = _get_float("rec_temperature") + if temperature_v is not None: + overrides["temperature"] = float(max(0.05, min(float(temperature_v), 100.0))) + + freshness_half_life_v = _get_float("rec_fresh_half_life_days") + if freshness_half_life_v is not None: + overrides["freshness_half_life_days"] = float(max(0.1, min(float(freshness_half_life_v), 3650.0))) + + velocity_smooth_v = _get_float("rec_velocity_smooth_days") + if velocity_smooth_v is not None: + overrides["velocity_smooth_days"] = float(max(0.0, min(float(velocity_smooth_v), 3650.0))) + + score_overrides: dict[str, float] = {} + for key in _DEFAULT_SCORE_WEIGHTS.keys(): + v = _get_float(f"rec_w_{key}") + if v is None: + continue + score_overrides[key] = float(max(-100.0, min(float(v), 100.0))) + if score_overrides: + overrides["score_weights"] = score_overrides + + mult_overrides: dict[str, float] = {} + for key in _DEFAULT_RECOMMENDATION["multipliers"].keys(): + v = _get_float(f"rec_m_{key}") + if v is None: + continue + mult_overrides[key] = float(max(0.0, min(float(v), 100.0))) + if mult_overrides: + overrides["multipliers"] = mult_overrides + + return overrides, used + + def _quality_score(image: Any, *, weights: dict[str, float] | None = None) -> float: w = weights or _DEFAULT_SCORE_WEIGHTS w_bookmark = float(w.get("bookmark", _DEFAULT_SCORE_WEIGHTS["bookmark"])) @@ -592,11 +704,72 @@ async def random_image( rng = random.Random(seed_norm) if seed_norm else random time_boost_enabled = not bool(seed_norm) - anti_repeat_enabled = bool(time_boost_enabled) and user_id is None and illust_id is None + dedup_enabled_setting = True + dedup_window_s = 20.0 * 60.0 + dedup_max_images = 5000 + dedup_max_authors = 2000 + dedup_strict = False + dedup_image_penalty = 8.0 + dedup_author_penalty = 2.5 + dedup_raw = random_defaults.get("dedup") + if isinstance(dedup_raw, dict): + v = _as_bool(dedup_raw.get("enabled")) + if v is not None: + dedup_enabled_setting = bool(v) + + window_raw = dedup_raw.get("window_s") + if window_raw is not None: + try: + dedup_window_s = float(max(0.0, min(float(window_raw), 24.0 * 60.0 * 60.0))) + except Exception: + pass + + max_images_raw = dedup_raw.get("max_images") + if max_images_raw is not None: + try: + dedup_max_images = int(max(1, min(int(max_images_raw), 200_000))) + except Exception: + pass + + max_authors_raw = dedup_raw.get("max_authors") + if max_authors_raw is not None: + try: + dedup_max_authors = int(max(1, min(int(max_authors_raw), 200_000))) + except Exception: + pass + + v = _as_bool(dedup_raw.get("strict")) + if v is not None: + dedup_strict = bool(v) + + image_pen_raw = dedup_raw.get("image_penalty") + if image_pen_raw is not None: + try: + v = float(image_pen_raw) + if math.isfinite(v): + dedup_image_penalty = float(max(0.0, min(v, 1000.0))) + except Exception: + pass + + author_pen_raw = dedup_raw.get("author_penalty") + if author_pen_raw is not None: + try: + v = float(author_pen_raw) + if math.isfinite(v): + dedup_author_penalty = float(max(0.0, min(v, 1000.0))) + except Exception: + pass + + anti_repeat_enabled = bool(dedup_enabled_setting) and bool(time_boost_enabled) and user_id is None and illust_id is None recent_image_ids: set[int] = set() recent_author_ids: set[int] = set() if anti_repeat_enabled: - recent_image_ids, recent_author_ids = _get_recent_sets(time.monotonic()) + recent_image_ids, recent_author_ids = _get_recent_sets( + time.monotonic(), + window_s=float(dedup_window_s), + max_images=int(dedup_max_images), + max_authors=int(dedup_max_authors), + ) strategy_raw = (strategy or "").strip().lower() strategy_source = "query" @@ -687,6 +860,21 @@ async def random_image( recommendation_source = "runtime" recommendation_obj = dict(recommendation_raw) + rec_overrides, rec_override_keys = _parse_recommendation_overrides_from_query(getattr(request, "query_params", None)) + if rec_overrides: + recommendation_source = "query" + # Shallow merge: keep unspecified runtime defaults, override only what user passes. + recommendation_obj = dict(recommendation_obj) + for k, v in rec_overrides.items(): + if k in {"score_weights", "multipliers"}: + base_raw = recommendation_obj.get(k) + base = dict(base_raw) if isinstance(base_raw, dict) else {} + if isinstance(v, dict): + base.update(v) + recommendation_obj[k] = base + else: + recommendation_obj[k] = v + pick_mode_raw = str(recommendation_obj.get("pick_mode") or _DEFAULT_RECOMMENDATION["pick_mode"]).strip().lower() if pick_mode_raw not in {"best", "weighted"}: pick_mode_raw = str(_DEFAULT_RECOMMENDATION["pick_mode"]) @@ -709,6 +897,20 @@ async def random_image( v = _as_float(multipliers_obj.get(key), default=float(default_value)) multipliers[key] = float(max(0.0, min(float(v), 100.0))) + freshness_half_life_days_default = float(_DEFAULT_RECOMMENDATION["freshness_half_life_days"]) + freshness_half_life_days = freshness_half_life_days_default + if "freshness_half_life_days" in recommendation_obj: + v = _as_float(recommendation_obj.get("freshness_half_life_days"), default=float("nan")) + if math.isfinite(float(v)): + freshness_half_life_days = float(max(0.1, min(float(v), 3650.0))) + + velocity_smooth_days_default = float(_DEFAULT_RECOMMENDATION["velocity_smooth_days"]) + velocity_smooth_days = velocity_smooth_days_default + if "velocity_smooth_days" in recommendation_obj: + v = _as_float(recommendation_obj.get("velocity_smooth_days"), default=float("nan")) + if math.isfinite(float(v)): + velocity_smooth_days = float(max(0.0, min(float(v), 3650.0))) + debug_base = { "attempts": int(attempts_i), "attempts_source": attempts_source, @@ -724,8 +926,18 @@ async def random_image( "quality_samples_scaled": bool(quality_samples_scaled), "quality_samples_source": quality_samples_source, "anti_repeat_enabled": bool(anti_repeat_enabled), + "dedup_enabled": bool(dedup_enabled_setting), + "dedup_window_s": float(dedup_window_s), + "dedup_max_images": int(dedup_max_images), + "dedup_max_authors": int(dedup_max_authors), + "dedup_strict": bool(dedup_strict), + "dedup_image_penalty": float(dedup_image_penalty), + "dedup_author_penalty": float(dedup_author_penalty), "time_boost_enabled": bool(time_boost_enabled), "recommendation_source": recommendation_source, + "recommendation_query_overrides": list(rec_override_keys or []), + "freshness_half_life_days": float(freshness_half_life_days), + "velocity_smooth_days": float(velocity_smooth_days), } async def _pick_with_strategy( @@ -740,7 +952,7 @@ async def random_image( exclude_set.update(int(x) for x in recent_image_ids) image = await pick_random_image(session, r=rng.random(), exclude_image_ids=list(exclude_set), **pick_kwargs) - if image is None and bool(anti_repeat_enabled) and recent_image_ids: + if image is None and bool(anti_repeat_enabled) and bool(recent_image_ids) and not bool(dedup_strict): image = await pick_random_image(session, r=rng.random(), exclude_image_ids=base_exclude, **pick_kwargs) if image is None: return None, {**debug_base, "attempts_used": 1, "picked_by": "random_key"} @@ -818,7 +1030,7 @@ async def random_image( illust_type_allowed=illust_allowed, **pick_kwargs, ) - if not images and bool(anti_repeat_enabled) and recent_image_ids: + if not images and bool(anti_repeat_enabled) and bool(recent_image_ids) and not bool(dedup_strict): images = await pick_random_images( session, r=rng.random(), @@ -834,23 +1046,25 @@ async def random_image( for image in images: score_base = _quality_score(image, weights=score_weights) - # 时间因素（适度）：默认使用 created_at_pixiv；若缺失则 freshness 退化到 added_at， - # 以便新导入/新补全的图片也能获得“新鲜感”提升。 + # 时间因素： + # - freshness: 对“老图”做衰减（loss），避免老热门长期统治（可通过权重/半衰期调节强度）。 + # - bookmark_velocity: 提升“成长速度快”的作品，避免只看总收藏数。 + # + # 默认使用 created_at_pixiv；若缺失则 freshness 退化到 added_at，以便新导入/新补全的图片也能有时间信号。 freshness_w = float(score_weights.get("freshness", 0.0)) if bool(time_boost_enabled) else 0.0 velocity_w = float(score_weights.get("bookmark_velocity", 0.0)) if bool(time_boost_enabled) else 0.0 freshness_contrib = 0.0 velocity_contrib = 0.0 if freshness_w != 0.0: - # 半衰期固定为 21 天：足够提升新图，但不会让老图完全失去竞争力。 - half_life_days = 21.0 dt_created = _parse_iso_dt(getattr(image, "created_at_pixiv", None)) if dt_created is None: dt_created = _parse_iso_dt(getattr(image, "added_at", None)) age_days = _age_days(dt_created) if age_days is not None: try: - freshness_contrib = float(freshness_w) * math.exp(-float(age_days) / float(half_life_days)) + # log(decay) = - age/half_life, i.e. a true time-decay loss factor. + freshness_contrib = (-1.0) * float(freshness_w) * (float(age_days) / float(freshness_half_life_days)) except Exception: freshness_contrib = 0.0 @@ -860,8 +1074,8 @@ async def random_image( bookmark_count = _as_nonneg_int(getattr(image, "bookmark_count", None)) if age_days is not None and bookmark_count > 0: try: - # +2 天平滑，避免“刚发布/刚补全”的极端值。 - denom = float(age_days) + 2.0 + # 平滑，避免“刚发布/刚补全”的极端值。 + denom = float(age_days) + float(velocity_smooth_days) velocity_term = math.log1p(float(bookmark_count) / max(1.0, denom)) velocity_contrib = float(velocity_w) * float(velocity_term) except Exception: @@ -876,13 +1090,13 @@ async def random_image( if bool(anti_repeat_enabled): try: if int(getattr(image, "id", 0) or 0) in recent_image_ids: - logit -= 8.0 + logit -= float(dedup_image_penalty) except Exception: pass try: uid = getattr(image, "user_id", None) if uid is not None and int(uid) in recent_author_ids: - logit -= 2.5 + logit -= float(dedup_author_penalty) except Exception: pass candidates.append( @@ -979,6 +1193,9 @@ async def random_image( now=time.monotonic(), image_id=int(image.id), user_id=int(image.user_id) if getattr(image, "user_id", None) is not None else None, + window_s=float(dedup_window_s), + max_images=int(dedup_max_images), + max_authors=int(dedup_max_authors), ) except Exception: pass @@ -1146,7 +1363,14 @@ async def random_image( ) if bool(anti_repeat_enabled): try: - _record_recent(now=time.monotonic(), image_id=int(image_id), user_id=user_id_for_recent) + _record_recent( + now=time.monotonic(), + image_id=int(image_id), + user_id=user_id_for_recent, + window_s=float(dedup_window_s), + max_images=int(dedup_max_images), + max_authors=int(dedup_max_authors), + ) except Exception: pass if should_mark_ok: diff --git a/backend/tests/test_admin_settings_get.py b/backend/tests/test_admin_settings_get.py index 0691aa4..864ecd9 100644 --- a/backend/tests/test_admin_settings_get.py +++ b/backend/tests/test_admin_settings_get.py @@ -74,10 +74,19 @@ def test_admin_get_settings_returns_defaults_and_runtime_overrides(tmp_path: Pat assert settings["random"]["fail_cooldown_ms"] == 600000 assert settings["random"]["strategy"] == "quality" assert settings["random"]["quality_samples"] == 12 + assert settings["random"]["dedup"]["enabled"] is True + assert settings["random"]["dedup"]["window_s"] == 1200 + assert settings["random"]["dedup"]["max_images"] == 5000 + assert settings["random"]["dedup"]["max_authors"] == 2000 + assert settings["random"]["dedup"]["strict"] is False + assert settings["random"]["dedup"]["image_penalty"] == 8.0 + assert settings["random"]["dedup"]["author_penalty"] == 2.5 recommendation = settings["random"]["recommendation"] assert recommendation["pick_mode"] == "weighted" assert recommendation["temperature"] == 1.0 + assert recommendation["freshness_half_life_days"] == 21.0 + assert recommendation["velocity_smooth_days"] == 2.0 assert recommendation["score_weights"]["bookmark"] == 4.0 assert recommendation["score_weights"]["view"] == 0.5 assert recommendation["multipliers"]["ai"] == 1.0 diff --git a/backend/tests/test_admin_settings_put.py b/backend/tests/test_admin_settings_put.py index f31fb34..14df142 100644 --- a/backend/tests/test_admin_settings_put.py +++ b/backend/tests/test_admin_settings_put.py @@ -84,8 +84,12 @@ def test_admin_put_settings_updates_and_get_reflects(tmp_path: Path, monkeypatch assert settings["random"]["fail_cooldown_ms"] == 12345 assert settings["random"]["strategy"] == "random" assert settings["random"]["quality_samples"] == 7 + assert settings["random"]["dedup"]["enabled"] is True + assert settings["random"]["dedup"]["window_s"] == 1200 assert settings["random"]["recommendation"]["pick_mode"] == "best" assert settings["random"]["recommendation"]["temperature"] == 2.5 + assert settings["random"]["recommendation"]["freshness_half_life_days"] == 21.0 + assert settings["random"]["recommendation"]["velocity_smooth_days"] == 2.0 assert settings["random"]["recommendation"]["score_weights"]["bookmark"] == 10.0 assert settings["random"]["recommendation"]["score_weights"]["view"] == 1.0 assert settings["random"]["recommendation"]["multipliers"]["ai"] == 0.5 diff --git a/backend/tests/test_random_quality_strategy.py b/backend/tests/test_random_quality_strategy.py index 408ffba..1b04e5e 100644 --- a/backend/tests/test_random_quality_strategy.py +++ b/backend/tests/test_random_quality_strategy.py @@ -157,6 +157,87 @@ def test_random_quality_strategy_picks_weighted_by_score(tmp_path: Path, monkeyp assert isinstance(body["data"]["debug"]["quality_score"], float) +def test_random_quality_strategy_supports_rec_query_overrides(tmp_path: Path, monkeypatch) -> None: + db_path = tmp_path / "random_quality_rec_overrides.db" + db_url = "sqlite+aiosqlite:///" + db_path.as_posix() + + monkeypatch.setenv("APP_ENV", "dev") + monkeypatch.setenv("DATABASE_URL", db_url) + + app = create_app() + + async def _seed() -> None: + async with app.state.engine.begin() as conn: + await conn.run_sync(Base.metadata.create_all) + + Session = create_sessionmaker(app.state.engine) + async with Session() as session: + session.add_all( + [ + Image( + illust_id=11, + page_index=0, + ext="jpg", + original_url="https://example.test/11.jpg", + proxy_path="/i/11.jpg", + random_key=0.10, + x_restrict=0, + ai_type=0, + illust_type=0, + width=1000, + height=1000, + bookmark_count=100, + view_count=100, + comment_count=0, + ), + Image( + illust_id=22, + page_index=0, + ext="jpg", + original_url="https://example.test/22.jpg", + proxy_path="/i/22.jpg", + random_key=0.20, + x_restrict=0, + ai_type=0, + illust_type=0, + width=1000, + height=1000, + bookmark_count=1, + view_count=100000, + comment_count=0, + ), + ] + ) + await session.commit() + + await app.state.engine.dispose() + + asyncio.run(_seed()) + + with TestClient(app) as client: + resp = client.get( + "/random", + params={ + "format": "json", + "attempts": 1, + "seed": "seed_rec_override_001", + "strategy": "quality", + "quality_samples": 2, + "rec_pick_mode": "best", + "rec_w_bookmark": 0, + "rec_w_view": 2, + "rec_w_comment": 0, + "rec_w_pixels": 0, + "rec_w_bookmark_rate": 0, + }, + ) + assert resp.status_code == 200 + body = resp.json() + assert body["ok"] is True + # With bookmark weight disabled and view weight boosted, the high-view image should win. + assert int(body["data"]["image"]["illust_id"]) == 22 + + def test_random_strategy_random_key_matches_pick_random_image(tmp_path: Path, monkeypatch) -> None: db_path = tmp_path / "random_strategy_random_key.db" db_url = "sqlite+aiosqlite:///" + db_path.as_posix() diff --git a/frontend/src/pages/RecommendationPage.test.tsx b/frontend/src/pages/RecommendationPage.test.tsx index a2f839b..3e81643 100644 --- a/frontend/src/pages/RecommendationPage.test.tsx +++ b/frontend/src/pages/RecommendationPage.test.tsx @@ -24,8 +24,17 @@ describe("RecommendationPage", () => { const body = init.body ? JSON.parse(String(init.body)) : {}; expect(body.settings.random.strategy).toBe("quality"); expect(body.settings.random.quality_samples).toBe(12); + expect(body.settings.random.dedup.enabled).toBe(true); + expect(body.settings.random.dedup.window_s).toBe(1200); + expect(body.settings.random.dedup.max_images).toBe(5000); + expect(body.settings.random.dedup.max_authors).toBe(2000); + expect(body.settings.random.dedup.strict).toBe(false); + expect(body.settings.random.dedup.image_penalty).toBe(8); + expect(body.settings.random.dedup.author_penalty).toBe(2.5); expect(body.settings.random.recommendation.pick_mode).toBe("weighted"); expect(body.settings.random.recommendation.temperature).toBe(1); + expect(body.settings.random.recommendation.freshness_half_life_days).toBe(21); + expect(body.settings.random.recommendation.velocity_smooth_days).toBe(2); expect(body.settings.random.recommendation.score_weights.bookmark).toBe(4); expect(body.settings.random.recommendation.score_weights.freshness).toBe(1); expect(body.settings.random.recommendation.score_weights.bookmark_velocity).toBe(1.2); @@ -44,9 +53,20 @@ describe("RecommendationPage", () => { random: { strategy: "quality", quality_samples: 12, + dedup: { + enabled: true, + window_s: 1200, + max_images: 5000, + max_authors: 2000, + strict: false, + image_penalty: 8, + author_penalty: 2.5, + }, recommendation: { pick_mode: "weighted", temperature: 1, + freshness_half_life_days: 21, + velocity_smooth_days: 2, score_weights: { bookmark: 4, view: 0.5, comment: 2, pixels: 1, bookmark_rate: 3, freshness: 1, bookmark_velocity: 1.2 }, multipliers: { ai: 1, diff --git a/frontend/src/pages/RecommendationPage.tsx b/frontend/src/pages/RecommendationPage.tsx index 0c31a55..f01583b 100644 --- a/frontend/src/pages/RecommendationPage.tsx +++ b/frontend/src/pages/RecommendationPage.tsx @@ -1,5 +1,5 @@ import { useMutation, useQuery, useQueryClient } from "@tanstack/react-query"; -import { Alert, Button, Card, Form, Input, InputNumber, Select, Skeleton, Space, Typography } from "antd"; +import { Alert, Button, Card, Form, Input, InputNumber, Select, Skeleton, Space, Switch, Typography } from "antd"; import React, { useEffect, useMemo, useState } from "react"; import { ApiError, apiJson } from "../api/client"; @@ -35,6 +35,8 @@ type FormValues = { w_bookmark_rate: number; w_freshness: number; w_bookmark_velocity: number; + freshness_half_life_days: number; + velocity_smooth_days: number; m_ai: number; m_non_ai: number; @@ -44,6 +46,14 @@ type FormValues = { m_ugoira: number; m_unknown_illust_type: number; + dedup_enabled: boolean; + dedup_window_s: number; + dedup_max_images: number; + dedup_max_authors: number; + dedup_strict: boolean; + dedup_image_penalty: number; + dedup_author_penalty: number; + preview_seed: string; }; @@ -62,6 +72,8 @@ const DEFAULTS: Omit = { w_bookmark_rate: 3.0, w_freshness: 1.0, w_bookmark_velocity: 1.2, + freshness_half_life_days: 21.0, + velocity_smooth_days: 2.0, m_ai: 1.0, m_non_ai: 1.0, m_unknown_ai: 1.0, @@ -69,6 +81,13 @@ const DEFAULTS: Omit = { m_manga: 1.0, m_ugoira: 1.0, m_unknown_illust_type: 1.0, + dedup_enabled: true, + dedup_window_s: 20 * 60, + dedup_max_images: 5000, + dedup_max_authors: 2000, + dedup_strict: false, + dedup_image_penalty: 8.0, + dedup_author_penalty: 2.5, }; function requestIdFromError(err: unknown): string | null { @@ -81,6 +100,17 @@ function asObject(value: unknown): Record { return value as Record; } +function asBool(value: unknown, fallback: boolean): boolean { + if (typeof value === "boolean") return value; + if (typeof value === "number" && (value === 0 || value === 1)) return Boolean(value); + if (typeof value === "string") { + const normalized = value.trim().toLowerCase(); + if (normalized === "true" || normalized === "1" || normalized === "yes" || normalized === "on") return true; + if (normalized === "false" || normalized === "0" || normalized === "no" || normalized === "off") return false; + } + return fallback; +} + function asInt(value: unknown, fallback: number): number { if (typeof value === "number" && Number.isFinite(value)) return Math.trunc(value); if (typeof value === "string") { @@ -138,6 +168,7 @@ export function RecommendationPage() { const settings = asObject(query.data.settings); const random = asObject(settings.random); const recommendation = asObject(random.recommendation); + const dedup = asObject(random.dedup); const scoreWeights = asObject(recommendation.score_weights); const multipliers = asObject(recommendation.multipliers); @@ -146,6 +177,8 @@ export function RecommendationPage() { random_quality_samples: asInt(random.quality_samples, DEFAULTS.random_quality_samples), pick_mode: asLowerEnum(recommendation.pick_mode, PICK_MODE_VALUES, DEFAULTS.pick_mode), temperature: asFloat(recommendation.temperature, DEFAULTS.temperature), + freshness_half_life_days: asFloat(recommendation.freshness_half_life_days, DEFAULTS.freshness_half_life_days), + velocity_smooth_days: asFloat(recommendation.velocity_smooth_days, DEFAULTS.velocity_smooth_days), w_bookmark: asFloat(scoreWeights.bookmark, DEFAULTS.w_bookmark), w_view: asFloat(scoreWeights.view, DEFAULTS.w_view), w_comment: asFloat(scoreWeights.comment, DEFAULTS.w_comment), @@ -160,6 +193,13 @@ export function RecommendationPage() { m_manga: asFloat(multipliers.manga, DEFAULTS.m_manga), m_ugoira: asFloat(multipliers.ugoira, DEFAULTS.m_ugoira), m_unknown_illust_type: asFloat(multipliers.unknown_illust_type, DEFAULTS.m_unknown_illust_type), + dedup_enabled: asBool(dedup.enabled, DEFAULTS.dedup_enabled), + dedup_window_s: asInt(dedup.window_s, DEFAULTS.dedup_window_s), + dedup_max_images: asInt(dedup.max_images, DEFAULTS.dedup_max_images), + dedup_max_authors: asInt(dedup.max_authors, DEFAULTS.dedup_max_authors), + dedup_strict: asBool(dedup.strict, DEFAULTS.dedup_strict), + dedup_image_penalty: asFloat(dedup.image_penalty, DEFAULTS.dedup_image_penalty), + dedup_author_penalty: asFloat(dedup.author_penalty, DEFAULTS.dedup_author_penalty), preview_seed: "", }); }, [form, query.data]); @@ -172,8 +212,8 @@ export function RecommendationPage() { "+ w_comment * ln(1 + comment_count)", "+ w_pixels * ln(1 + (width*height)/1_000_000)", "+ w_bookmark_rate * ln(1 + (bookmark_count/view_count)*1000)", - "+ w_freshness * exp(-age_days / 21)", - "+ w_bookmark_velocity * ln(1 + bookmark_count / (age_days + 2))", + "- w_freshness * (age_days / freshness_half_life_days)", + "+ w_bookmark_velocity * ln(1 + bookmark_count / (age_days + velocity_smooth_days))", "", "说明：有 seed 时，为保证可复现，会自动关闭 freshness/bookmark_velocity 两项。", "最终得分会再乘以“类别倍率”（AI/插画/漫画/动图等）。", @@ -190,9 +230,20 @@ export function RecommendationPage() { random: { strategy: values.random_strategy, quality_samples: values.random_quality_samples, + dedup: { + enabled: values.dedup_enabled, + window_s: Math.max(0, Math.trunc(values.dedup_window_s || 0)), + max_images: Math.max(1, Math.trunc(values.dedup_max_images || 1)), + max_authors: Math.max(1, Math.trunc(values.dedup_max_authors || 1)), + strict: values.dedup_strict, + image_penalty: values.dedup_image_penalty, + author_penalty: values.dedup_author_penalty, + }, recommendation: { pick_mode: values.pick_mode, temperature: values.temperature, + freshness_half_life_days: values.freshness_half_life_days, + velocity_smooth_days: values.velocity_smooth_days, score_weights: { bookmark: values.w_bookmark, view: values.w_view, @@ -374,6 +425,36 @@ export function RecommendationPage() { + + 全局防重复（dedup） + + + 开启后，同一张图片在窗口期内会尽量不重复返回（进程内 best-effort；严格模式可禁止回退重复）。 + + + + + + + + + + + + + + + + + + + + + + + + + 评分公式（score_weights） @@ -396,16 +477,22 @@ export function RecommendationPage() { - + + + + + + + diff --git a/frontend/src/pages/SettingsPage.test.tsx b/frontend/src/pages/SettingsPage.test.tsx index c94b2f0..4aaa443 100644 --- a/frontend/src/pages/SettingsPage.test.tsx +++ b/frontend/src/pages/SettingsPage.test.tsx @@ -34,7 +34,7 @@ describe("SettingsPage", () => { expect(body.settings.random.default_r18_strict).toBe(true); expect(body.settings.random.fail_cooldown_ms).toBe(600000); expect(body.settings.random.strategy).toBe("quality"); - expect(body.settings.random.quality_samples).toBe(5); + expect(body.settings.random.quality_samples).toBe(12); expect(body.settings.security.hide_origin_url_in_public_json).toBe(true); expect(body.settings.rate_limit.pixiv_hydrate_min_interval_ms).toBe(800); expect(body.settings.rate_limit.pixiv_hydrate_jitter_ms).toBe(200); @@ -56,7 +56,7 @@ describe("SettingsPage", () => { default_pool_id: "", }, image_proxy: { use_pixiv_cat: false, pximg_mirror_host: "i.pixiv.cat", extra_pximg_mirror_hosts: [] }, - random: { default_attempts: 3, default_r18_strict: true, fail_cooldown_ms: 600000, strategy: "quality", quality_samples: 5 }, + random: { default_attempts: 3, default_r18_strict: true, fail_cooldown_ms: 600000, strategy: "quality", quality_samples: 12 }, security: { hide_origin_url_in_public_json: true }, rate_limit: {}, }, diff --git a/frontend/src/pages/SettingsPage.tsx b/frontend/src/pages/SettingsPage.tsx index dc15218..8e896a2 100644 --- a/frontend/src/pages/SettingsPage.tsx +++ b/frontend/src/pages/SettingsPage.tsx @@ -153,7 +153,7 @@ export function SettingsPage() { random_default_r18_strict: asBool(random.default_r18_strict, true), random_fail_cooldown_ms: asInt(random.fail_cooldown_ms, 600_000), random_strategy: asLowerEnum(random.strategy, RANDOM_STRATEGY_VALUES, "quality"), - random_quality_samples: asInt(random.quality_samples, 5), + random_quality_samples: asInt(random.quality_samples, 12), security_hide_origin_url_in_public_json: asBool(security.hide_origin_url_in_public_json, true), pixiv_hydrate_min_interval_ms: asInt(rateLimit.pixiv_hydrate_min_interval_ms, 800), pixiv_hydrate_jitter_ms: asInt(rateLimit.pixiv_hydrate_jitter_ms, 200),