mission-control-v2/backend/services/llamaswap.py

"""
Engine-Service: liest/schreibt die llama-swap config.yaml und spricht die
llama-swap-API. Portiert & erweitert aus Mission Control v1.

NEU in 2.0: `groups` für Ko-Residenz (schnell + schwer gleichzeitig geladen,
`swap:false`) → Multi-Model-Delegation ohne Nachlade-Latenz.
"""

import os
import re

import httpx
from ruamel.yaml.scalarstring import LiteralScalarString

from config import CMD_TEMPLATE, CONFIG_PATH, DEFAULT_TTL, LLAMA_SWAP_URL, yaml

# Kanonische Rollen (vereinheitlicht ggü. v1: kein manager/reviewer mehr).
ROLE_IDS = {"vision", "coder", "reasoning", "agent", "scout"}

_CTX_RE = re.compile(r"-(?:c|-ctx-size)\s+(\d+)")
_PATH_RE = re.compile(r"-(?:m|-model)\s+([^\s]+)")
_QUANT_RE = re.compile(r"(Q\d_[A-Z0-9_]+|IQ\d_[A-Z0-9_]+|fp16|bf16)\.gguf", re.IGNORECASE)


# --- Lesen -------------------------------------------------------------------
def read_config() -> dict:
    if not CONFIG_PATH.exists():
        return {"models": {}}
    with CONFIG_PATH.open("r", encoding="utf-8") as f:
        data = yaml.load(f) or {}
    if not data.get("models"):
        data["models"] = {}
    return data


def _parse_model(name: str, spec: dict) -> dict:
    spec = spec or {}
    cmd = str(spec.get("cmd", "")).strip()
    ctx = int(m.group(1)) if (m := _CTX_RE.search(cmd)) else None

    path = filename = quant = ""
    size_bytes = None
    if (m := _PATH_RE.search(cmd)):
        path = m.group(1).replace("'", "").replace('"', "")
        filename = os.path.basename(path)
        if os.path.exists(path):
            size_bytes = os.path.getsize(path)
        if (q := _QUANT_RE.search(path)):
            quant = q.group(1).upper()

    aliases = spec.get("aliases") or []
    if isinstance(aliases, str):
        aliases = [aliases]
    aliases = [str(a) for a in aliases]
    role = aliases[0].lower() if aliases else (name.lower() if name.lower() in ROLE_IDS else None)

    from services.caps import capabilities
    return {
        "name": name,
        "role": role,
        "aliases": aliases,
        "api_ids": [name] + aliases,
        "ctx": ctx,
        "ttl": spec.get("ttl"),
        "cmd": cmd,
        "gguf_path": path,
        "filename": filename,
        "quant": quant,
        "size_bytes": size_bytes,
        "incomplete": not path,
        "capabilities": capabilities(
            name=filename or name, cmd=cmd,
            gguf_path=(path if (path and os.path.exists(path)) else ""),
        ),
    }


def list_models() -> list[dict]:
    cfg = read_config()
    return [_parse_model(name, spec) for name, spec in (cfg.get("models") or {}).items()]


def engine_reachable() -> bool:
    try:
        with httpx.Client(timeout=3.0) as c:
            return c.get(f"{LLAMA_SWAP_URL}/v1/models").status_code == 200
    except Exception:
        return False


# --- Schreiben ---------------------------------------------------------------
def model_id_from_path(model_path: str) -> str:
    """Sprechende Modell-ID (= API-Name) aus dem GGUF-Pfad: Repo-Ordnername ohne
    '-GGUF'. Fallback: Dateiname ohne Quant-Suffix.
    Split-GGUFs liegen oft in einem Quant-Unterordner (…/Q4_K_M/file-00001-of-…) →
    dann eine Ebene höher (Repo-Ordner) nehmen, sonst hieße das Modell 'Q4_K_M'."""
    d = os.path.basename(os.path.dirname(model_path))
    if re.fullmatch(r"(I?Q\d[\w]*|UD-Q\d[\w]*|F16|BF16|FP16|F32)", d, flags=re.I):
        d = os.path.basename(os.path.dirname(os.path.dirname(model_path)))
    name = re.sub(r"[-_]?GGUF$", "", d, flags=re.I).strip("-_")
    if not name:
        fn = re.sub(r"\.gguf$", "", os.path.basename(model_path), flags=re.I)
        fn = re.sub(r"-\d+-of-\d+$", "", fn)
        name = re.sub(r"[-_](Q\d[\w]*|IQ\d[\w]*|F16|BF16|FP16|F32)$", "", fn, flags=re.I)
    return name or "modell"


def set_role_alias(cfg: dict, model_id: str, role: str | None) -> None:
    """Rolle als eindeutigen llama-swap-`aliases`-Eintrag setzen (vorher bei allen
    anderen Modellen entfernen). role=None/leer entfernt den Alias."""
    models = cfg.get("models") or {}
    role = (role or "").strip().lower()
    if role:
        for mid, spec in models.items():
            if mid == model_id or not isinstance(spec, dict):
                continue
            al = [a for a in (spec.get("aliases") or []) if str(a).lower() != role]
            if al:
                spec["aliases"] = al
            else:
                spec.pop("aliases", None)
    spec = models.get(model_id)
    if isinstance(spec, dict):
        if role and role != model_id.lower():
            spec["aliases"] = [role]
        else:
            spec.pop("aliases", None)


def _augment_vision(cmd: str, model_path: str, mmproj_path: str | None) -> str:
    """Vision-Modelle brauchen --mmproj <projektor> und --jinja."""
    if mmproj_path:
        if "--mmproj" not in cmd:
            cmd += f" --mmproj {mmproj_path}"
        if "--jinja" not in cmd:
            cmd += " --jinja"
    return cmd


def write_config(cfg: dict) -> None:
    """Atomar schreiben (tmp + os.replace), damit llama-swap mit -watch-config nie
    eine halbe Datei sieht. Fehlende Schreibrechte → klare Meldung."""
    try:
        CONFIG_PATH.parent.mkdir(parents=True, exist_ok=True)
        tmp = CONFIG_PATH.with_name(CONFIG_PATH.name + ".tmp")
        with tmp.open("w", encoding="utf-8") as f:
            yaml.dump(cfg, f)
        os.replace(tmp, CONFIG_PATH)
    except PermissionError as exc:
        raise PermissionError(
            f"Mission Control darf '{CONFIG_PATH}' nicht schreiben. "
            f"Einmalig: sudo chown -R hitonabi:hitonabi {CONFIG_PATH.parent}"
        ) from exc


def register_model(model_path: str, role: str | None = None, ctx: int = 8192,
                   ttl: int | None = None, mmproj_path: str | None = None,
                   jinja: bool = False) -> str:
    """Ein GGUF als llama-swap-Modell eintragen (cmd + Rolle-Alias). Gibt die
    Modell-ID zurück. jinja=True erzwingt --jinja (Tool-Calling, z.B. fürs Agent-Hirn)."""
    cfg = read_config()
    model_id = model_id_from_path(model_path)
    cmd = CMD_TEMPLATE.replace("{model}", model_path).replace("{ctx}", str(ctx))
    cmd = _augment_vision(cmd, model_path, mmproj_path)
    if jinja and "--jinja" not in cmd:
        cmd += " --jinja"
    cfg.setdefault("models", {})[model_id] = {
        "cmd": LiteralScalarString(cmd + "\n"),
        "ttl": ttl if ttl is not None else DEFAULT_TTL,
    }
    set_role_alias(cfg, model_id, role)
    write_config(cfg)
    return model_id


# --- Groups (Ko-Residenz) ----------------------------------------------------
def set_group(group: str, members: list[str], swap: bool = False, persist: bool = False) -> None:
    """llama-swap-`groups`-Eintrag setzen. swap=False → alle Mitglieder dürfen
    GLEICHZEITIG laufen (Ko-Residenz, keine Nachlade-Latenz). persist=True →
    Mitglieder werden nie automatisch entladen."""
    cfg = read_config()
    groups = cfg.setdefault("groups", {})
    groups[group] = {"swap": swap, "persist": persist, "members": list(members)}
    write_config(cfg)


def list_groups() -> dict:
    return read_config().get("groups") or {}