unsloth/studio/backend/routes/settings.py

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0

from typing import Literal, Optional
from urllib.parse import unquote, urlsplit

from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel, ConfigDict, Field, field_validator

from auth.authentication import get_current_subject
from auth.storage import rotate_preview_link_secret
from loggers import get_logger
from utils.utils import safe_error_detail, log_and_http_error
from utils.personalization_settings import (
    MAX_AVATAR_DATA_URL_BYTES,
    PERSONALIZATION_VERSION,
    get_personalization,
    set_personalization,
)
from utils.upload_limits import (
    MAX_UPLOAD_LIMIT_MB,
    MIN_UPLOAD_LIMIT_MB,
    default_upload_limit_mb,
    get_upload_limit_mb,
    set_upload_limit_mb,
    upload_limit_bytes,
    upload_limit_label,
)
from utils.helper_precache_settings import (
    DEFAULT_HELPER_PRECACHE_ENABLED,
    get_helper_precache_enabled,
    helper_model_disabled_by_env,
    set_helper_precache_enabled,
)
from utils.openai_auto_switch_settings import (
    DEFAULT_AUTO_UNLOAD_IDLE_SECONDS,
    DEFAULT_OPENAI_AUTO_SWITCH_ENABLED,
    get_auto_unload_idle_seconds,
    get_model_overrides,
    get_openai_auto_switch_enabled,
    get_stored_auto_unload_idle_seconds,
    set_model_override,
    set_openai_auto_switch,
)
from utils.preview_sharing_settings import (
    DEFAULT_PREVIEW_SHARING_ENABLED,
    get_preview_sharing_enabled,
    set_preview_sharing_enabled,
)
from utils.embedding_model_settings import (
    MAX_EMBEDDING_MODEL_LENGTH,
    default_embedding_model,
    get_rag_embedding_model,
    get_stored_embedding_model,
    reset_rag_embedding_model,
    set_rag_embedding_model,
    validate_embedding_model,
)

router = APIRouter()

logger = get_logger(__name__)


class UploadLimitPayload(BaseModel):
    max_upload_size_mb: int = Field(..., ge = MIN_UPLOAD_LIMIT_MB, le = MAX_UPLOAD_LIMIT_MB)


class UploadLimitResponse(BaseModel):
    max_upload_size_mb: int
    max_upload_size_bytes: int
    max_upload_size_label: str
    default_upload_size_mb: int
    min_upload_size_mb: int = MIN_UPLOAD_LIMIT_MB
    max_allowed_upload_size_mb: int = MAX_UPLOAD_LIMIT_MB


class HelperPrecachePayload(BaseModel):
    enabled: bool


class HelperPrecacheResponse(BaseModel):
    enabled: bool
    default_enabled: bool = DEFAULT_HELPER_PRECACHE_ENABLED
    disabled_by_env: bool


class OpenAIAutoSwitchPayload(BaseModel):
    enabled: bool
    auto_unload_idle_seconds: int = Field(default = DEFAULT_AUTO_UNLOAD_IDLE_SECONDS, ge = 0)


class OpenAIAutoSwitchResponse(BaseModel):
    enabled: bool
    auto_unload_idle_seconds: int
    default_enabled: bool = DEFAULT_OPENAI_AUTO_SWITCH_ENABLED
    # True when the idle-unload loop will actually unload (effective TTL > 0). With
    # UNSLOTH_MODEL_IDLE_TTL set and nothing stored, this is true even while enabled
    # is false, so the UI can show idle-unload as active instead of "needs enable".
    idle_unload_active: bool = False


class ModelOverridePayload(BaseModel):
    model_id: str = Field(..., min_length = 1)
    llama_extra_args: list[str] = Field(default_factory = list)
    # ge=1: 0 is not a valid sequence length, and the setter drops a falsy value,
    # so reject it at the boundary instead of accepting then silently discarding it.
    max_seq_length: Optional[int] = Field(default = None, ge = 1, le = 1048576)


class ModelOverridesResponse(BaseModel):
    overrides: dict[str, dict]


def _upload_limit_response(limit_mb: int) -> UploadLimitResponse:
    return UploadLimitResponse(
        max_upload_size_mb = limit_mb,
        max_upload_size_bytes = upload_limit_bytes(limit_mb),
        max_upload_size_label = upload_limit_label(limit_mb),
        default_upload_size_mb = default_upload_limit_mb(),
    )


def _helper_precache_response(enabled: bool | None = None) -> HelperPrecacheResponse:
    return HelperPrecacheResponse(
        enabled = get_helper_precache_enabled() if enabled is None else enabled,
        disabled_by_env = helper_model_disabled_by_env(),
    )


@router.get("/upload-limit", response_model = UploadLimitResponse)
def get_upload_limit(current_subject: str = Depends(get_current_subject)) -> UploadLimitResponse:
    return _upload_limit_response(get_upload_limit_mb())


@router.put("/upload-limit", response_model = UploadLimitResponse)
def update_upload_limit(
    payload: UploadLimitPayload, current_subject: str = Depends(get_current_subject)
) -> UploadLimitResponse:
    try:
        limit_mb = set_upload_limit_mb(payload.max_upload_size_mb)
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid upload limit."),
            event = "settings.update_upload_limit_failed",
            log = logger,
        ) from exc
    return _upload_limit_response(limit_mb)


@router.get("/helper-precache", response_model = HelperPrecacheResponse)
def get_helper_precache(
    current_subject: str = Depends(get_current_subject),
) -> HelperPrecacheResponse:
    return _helper_precache_response()


@router.put("/helper-precache", response_model = HelperPrecacheResponse)
def update_helper_precache(
    payload: HelperPrecachePayload, current_subject: str = Depends(get_current_subject)
) -> HelperPrecacheResponse:
    try:
        enabled = set_helper_precache_enabled(payload.enabled)
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid Helper LLM pre-cache setting."),
            event = "settings.update_helper_precache_failed",
            log = logger,
        ) from exc
    return _helper_precache_response(enabled)


@router.get("/openai-auto-switch", response_model = OpenAIAutoSwitchResponse)
def get_openai_auto_switch(
    current_subject: str = Depends(get_current_subject),
) -> OpenAIAutoSwitchResponse:
    return OpenAIAutoSwitchResponse(
        enabled = get_openai_auto_switch_enabled(),
        auto_unload_idle_seconds = get_stored_auto_unload_idle_seconds(),
        idle_unload_active = get_auto_unload_idle_seconds() > 0,
    )


@router.put("/openai-auto-switch", response_model = OpenAIAutoSwitchResponse)
def update_openai_auto_switch(
    payload: OpenAIAutoSwitchPayload, current_subject: str = Depends(get_current_subject)
) -> OpenAIAutoSwitchResponse:
    try:
        enabled, idle_seconds = set_openai_auto_switch(
            payload.enabled, payload.auto_unload_idle_seconds
        )
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid OpenAI auto-switch setting."),
            event = "settings.update_openai_auto_switch_failed",
            log = logger,
        ) from exc
    return OpenAIAutoSwitchResponse(
        enabled = enabled,
        auto_unload_idle_seconds = idle_seconds,
        idle_unload_active = get_auto_unload_idle_seconds() > 0,
    )


@router.get("/openai-auto-switch/overrides", response_model = ModelOverridesResponse)
def get_openai_auto_switch_overrides(
    current_subject: str = Depends(get_current_subject),
) -> ModelOverridesResponse:
    return ModelOverridesResponse(overrides = get_model_overrides())


@router.put("/openai-auto-switch/overrides", response_model = ModelOverridesResponse)
def update_openai_auto_switch_override(
    payload: ModelOverridePayload, current_subject: str = Depends(get_current_subject)
) -> ModelOverridesResponse:
    from core.inference.llama_server_args import validate_extra_args
    try:
        extra_args = validate_extra_args(payload.llama_extra_args)
        set_model_override(
            payload.model_id,
            llama_extra_args = extra_args,
            max_seq_length = payload.max_seq_length,
        )
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid model launch override."),
            event = "settings.update_model_override_failed",
            log = logger,
        ) from exc
    return ModelOverridesResponse(overrides = get_model_overrides())


class EmbeddingModelPayload(BaseModel):
    embedding_model: str = Field(..., min_length = 1, max_length = MAX_EMBEDDING_MODEL_LENGTH)
    # Token for gated/private repos during verification (not stored).
    hf_token: Optional[str] = Field(default = None, max_length = 512)
    # Skip HF verification (offline installs, local paths HF can't see).
    force: bool = False


class EmbeddingModelResponse(BaseModel):
    embedding_model: str
    default_embedding_model: str
    is_custom: bool


def _embedding_model_response() -> EmbeddingModelResponse:
    return EmbeddingModelResponse(
        embedding_model = get_rag_embedding_model(),
        default_embedding_model = default_embedding_model(),
        is_custom = get_stored_embedding_model() is not None,
    )


def _llama_backend_active() -> bool:
    """True when this install embeds via the llama-server (GGUF) backend."""
    from core.rag import config as rag_config
    from core.rag import embeddings

    try:
        raw = (rag_config.EMBED_BACKEND or "auto").strip().lower()
        key = embeddings._resolve_auto() if raw in embeddings._AUTO_ALIASES else raw
    except Exception:  # noqa: BLE001 - backend probe must never block saving
        return False
    return key in embeddings._LLAMA_ALIASES


def _resolves_as_local_gguf(model: str) -> bool:
    """True when ``model`` is a local .gguf file or a directory holding one, so
    a save on the llama-server backend needs no HF verification (the artifact
    itself is the proof)."""
    from core.rag.embed_llama_server import LlamaServerBackend
    try:
        return LlamaServerBackend._resolve_local_gguf(model) is not None
    except Exception:  # noqa: BLE001 - dir without .gguf, filesystem oddity
        return False


def _local_gguf_backend_error(model: str) -> str | None:
    """409 detail when ``model`` is a local dir without a .gguf but this install
    embeds via llama-server (macOS/CPU default), which needs one. A
    sentence-transformers-only folder would verify fine yet fail at first index.
    None when not applicable. ``force`` skips this check like HF verification."""
    from pathlib import Path

    if not Path(model).expanduser().is_dir():
        return None
    from core.rag.embed_llama_server import LlamaServerBackend

    if not _llama_backend_active():
        return None
    try:
        LlamaServerBackend._resolve_local_gguf(model)
        return None
    except RuntimeError:
        return (
            f"{model!r} contains no .gguf file, but this install embeds with the "
            "llama-server backend which requires one. Add a GGUF file to the "
            "folder or use a Hugging Face repo."
        )
    except Exception:  # noqa: BLE001 - filesystem oddity: don't block saving
        return None


def _hf_gguf_backend_error(model: str, hf_token: Optional[str]) -> str | None:
    """409 detail when the llama-server backend would find no .gguf for an HF
    repo: neither the derived companion repo nor the repo itself has one. Saves
    that verify as embedding models would otherwise fail at first index.
    None when not applicable; ``force`` skips this like HF verification."""
    from pathlib import Path

    if Path(model).expanduser().exists():
        return None  # local paths are handled by the local checks
    if not _llama_backend_active():
        return None
    from core.rag import config as rag_config

    candidates = [model] if rag_config._names_gguf(model) else [f"{model}-GGUF", model]
    try:
        from huggingface_hub import list_repo_files
    except Exception:  # noqa: BLE001 - hub client unavailable: don't block saving
        return None
    for candidate in candidates:
        try:
            files = list_repo_files(candidate, token = hf_token)
        except Exception:  # noqa: BLE001 - missing/gated repo: try next candidate
            continue
        if any(f.lower().endswith(".gguf") and "mmproj" not in f.lower() for f in files):
            return None
    checked = " or ".join(repr(c) for c in candidates)
    return (
        f"No GGUF weights found in {checked}, but this install embeds with the "
        "llama-server backend which requires them. Pick a model with a GGUF "
        "companion repo or GGUF files in the repo itself."
    )


@router.get("/embedding-model", response_model = EmbeddingModelResponse)
def get_embedding_model(
    current_subject: str = Depends(get_current_subject),
) -> EmbeddingModelResponse:
    return _embedding_model_response()


@router.put("/embedding-model", response_model = EmbeddingModelResponse)
def update_embedding_model(
    payload: EmbeddingModelPayload, current_subject: str = Depends(get_current_subject)
) -> EmbeddingModelResponse:
    """Set the RAG embedding model. Unless ``force`` is set, the repo is verified
    to be an embedding model via HF metadata; an unverifiable model (wrong type,
    typo, gated repo, or no network) returns 409 so the UI can offer "save anyway".
    Documents indexed under the previous model must be re-uploaded."""
    from utils.models import is_embedding_model

    try:
        model = validate_embedding_model(payload.embedding_model)
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid embedding model."),
            event = "settings.update_embedding_model_failed",
            log = logger,
        ) from exc
    # The env/default model needs no verification; saving it is a no-op override.
    # A local GGUF on the llama-server backend is accepted as-is: it is exactly
    # what the backend loads, and HF metadata cannot verify a local path.
    if (
        model != default_embedding_model()
        and not payload.force
        and not (_llama_backend_active() and _resolves_as_local_gguf(model))
    ):
        hf_token = (payload.hf_token or "").strip() or None
        from core.rag import config as rag_config

        # A GGUF-named repo on the llama-server backend is loaded from its .gguf
        # files, which rarely carry sentence-transformers metadata; verify the
        # GGUF is available (below) rather than the ST embedding-metadata gate,
        # which would wrongly 409 a valid online GGUF embedder.
        gguf_named = _llama_backend_active() and rag_config._names_gguf(model)
        if not gguf_named and not is_embedding_model(model, hf_token = hf_token):
            raise HTTPException(
                status_code = 409,
                detail = (
                    f"Could not verify {model!r} as an embedding model on "
                    "Hugging Face (it may be the wrong model type, gated, or "
                    "you may be offline)."
                ),
            )
        gguf_error = _local_gguf_backend_error(model) or _hf_gguf_backend_error(model, hf_token)
        if gguf_error:
            raise HTTPException(status_code = 409, detail = gguf_error)
    set_rag_embedding_model(model)
    logger.info(
        "settings.embedding_model_updated subject=%s model=%s forced=%s",
        current_subject,
        model,
        payload.force,
    )
    return _embedding_model_response()


@router.delete("/embedding-model", response_model = EmbeddingModelResponse)
def reset_embedding_model(
    current_subject: str = Depends(get_current_subject),
) -> EmbeddingModelResponse:
    """Clear the override, returning to the env/default model."""
    reset_rag_embedding_model()
    logger.info("settings.embedding_model_reset subject=%s", current_subject)
    return _embedding_model_response()


class PreviewLinkRotateResponse(BaseModel):
    rotated: bool = True


@router.post("/preview-links/rotate", response_model = PreviewLinkRotateResponse)
def rotate_preview_links(
    current_subject: str = Depends(get_current_subject),
) -> PreviewLinkRotateResponse:
    """Rotate the preview-link signing secret, revoking every previously shared `/p` link."""
    rotate_preview_link_secret()
    logger.info("settings.preview_links_rotated subject=%s", current_subject)
    return PreviewLinkRotateResponse(rotated = True)


class PreviewSharingPayload(BaseModel):
    enabled: bool


class PreviewSharingResponse(BaseModel):
    enabled: bool
    default_enabled: bool = DEFAULT_PREVIEW_SHARING_ENABLED


@router.get("/preview-sharing", response_model = PreviewSharingResponse)
def get_preview_sharing(
    current_subject: str = Depends(get_current_subject),
) -> PreviewSharingResponse:
    return PreviewSharingResponse(enabled = get_preview_sharing_enabled())


@router.put("/preview-sharing", response_model = PreviewSharingResponse)
def update_preview_sharing(
    payload: PreviewSharingPayload, current_subject: str = Depends(get_current_subject)
) -> PreviewSharingResponse:
    """Enable/disable the public `/p` preview surface. When off, links 404 even with a token."""
    try:
        enabled = set_preview_sharing_enabled(payload.enabled)
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid preview sharing setting."),
            event = "settings.update_preview_sharing_failed",
            log = logger,
        ) from exc
    logger.info("settings.preview_sharing_updated subject=%s enabled=%s", current_subject, enabled)
    return PreviewSharingResponse(enabled = enabled)


def _is_bundled_avatar_url(value: str) -> bool:
    parsed = urlsplit(value)
    if parsed.scheme or parsed.netloc:
        return False
    path = unquote(parsed.path).lstrip("/")
    if ".." in path.split("/"):
        return False
    marker = "Sloth emojis/"
    if marker not in path:
        return False
    return path[path.index(marker) :].lower().endswith(".png")


class PersonalizationProfile(BaseModel):
    model_config = ConfigDict(extra = "ignore")

    displayName: str = Field("", max_length = 200)
    nickname: str = Field("", max_length = 200)
    avatarDataUrl: Optional[str] = Field(None, max_length = MAX_AVATAR_DATA_URL_BYTES)
    avatarShape: Literal["circle", "rounded"] = "circle"

    @field_validator("avatarDataUrl")
    @classmethod
    def _validate_avatar(cls, value: Optional[str]) -> Optional[str]:
        if not value:
            return value
        if not value.startswith("data:image/") and not _is_bundled_avatar_url(value):
            raise ValueError("avatarDataUrl must be an image data URL or bundled avatar.")
        return value


class PersonalizationAppearance(BaseModel):
    model_config = ConfigDict(extra = "ignore")

    theme: Literal["light", "dark", "system"] = "system"
    language: Optional[str] = Field(None, max_length = 20)


class PersonalizationPayload(BaseModel):
    model_config = ConfigDict(extra = "ignore")

    version: int = PERSONALIZATION_VERSION
    profile: PersonalizationProfile = Field(default_factory = PersonalizationProfile)
    appearance: PersonalizationAppearance = Field(default_factory = PersonalizationAppearance)


class PersonalizationResponse(PersonalizationPayload):
    saved: bool = False


@router.get("/personalization", response_model = PersonalizationResponse)
def get_personalization_settings(
    current_subject: str = Depends(get_current_subject),
) -> PersonalizationResponse:
    stored = get_personalization()
    response = PersonalizationResponse.model_validate(stored or {})
    response.saved = bool(stored)
    return response


@router.put("/personalization", response_model = PersonalizationPayload)
def update_personalization_settings(
    payload: PersonalizationPayload, current_subject: str = Depends(get_current_subject)
) -> PersonalizationPayload:
    try:
        set_personalization(payload.model_dump())
    except ValueError as exc:
        raise log_and_http_error(
            exc,
            400,
            safe_error_detail(exc, fallback = "Invalid personalization settings."),
            event = "settings.update_personalization_failed",
            log = logger,
        ) from exc
    return payload