parththakkar106andClaude Opus 5
1dd31086c1
AI Chat is a plain scratchpad for talking to a model directly — no story context, scripts or world state — for poking at models, prompts and endpoints without starting an adventure. Power users only: the router 404s (rather than 403s) for everyone else and the nav link is hidden. The conversation lives in localStorage, so there's no new table or migration. is_power_user() now also returns True in local mode: it's the operator's own machine and their own key, the same reasoning that makes the provider debug log local-only. Alongside that, the rule keeping the shared demo key off paid models now lives in exactly one place. It had been duplicated into the chat router, which is how one copy eventually drifts: - resolve_provider_config() takes an optional model_override and is the only place the whitelist is applied, so turns, AI Chat and the connection test all inherit it. An override is a per-request preference, never a grant. - ProviderConfig.__post_init__ refuses to exist when api_key is the demo key and the model isn't whitelisted. It keys on the key itself rather than the using_demo flag, so a mislabelled config can't slip past, and it raises so a future path that bypasses the resolver fails loudly instead of billing. - The demo branch still pins endpoint_url too — a user-controlled endpoint would leak the key itself, which is worse than spending it. Provider gained chat(messages, ...) beside generate(), both delegating to a shared _stream(url, body); completion-mode endpoints get the messages flattened into a labelled transcript. Settings' /models fetch moved to list_endpoint_models() and is shared with /api/chat/config. Tests: 10 new in tests/test_chat.py (70 total). These deliberately do not stub resolve_provider_config — the point is to exercise the real BYOK-vs-demo decision and assert on what the provider actually received: off-whitelist override pinned, off-whitelist Settings.model pinned, redirected endpoint pinned, BYOK passed through untouched. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FGY1yvzSeKgTtRfeVtDmx
101 lines
3.7 KiB
Python
101 lines
3.7 KiB
Python
import httpx
|
|
from fastapi import APIRouter, Depends, Request
|
|
from sqlalchemy.orm import Session
|
|
|
|
from .. import auth, limits, models, schemas, security
|
|
from ..database import get_db
|
|
|
|
router = APIRouter(prefix="/api/settings", tags=["settings"])
|
|
|
|
|
|
def get_settings(db: Session, user: models.User) -> models.Settings:
|
|
"""Per-user settings row, created on first access (Phase 8: settings —
|
|
endpoint, key, models, memory config — are per user, not global)."""
|
|
settings = (
|
|
db.query(models.Settings).filter(models.Settings.user_id == user.id).first()
|
|
)
|
|
if settings is None:
|
|
settings = models.Settings(user_id=user.id)
|
|
db.add(settings)
|
|
db.commit()
|
|
return settings
|
|
|
|
|
|
@router.get("", response_model=schemas.SettingsOut)
|
|
def read_settings(
|
|
db: Session = Depends(get_db),
|
|
user: models.User = Depends(auth.get_current_user),
|
|
):
|
|
return get_settings(db, user)
|
|
|
|
|
|
@router.put("", response_model=schemas.SettingsOut)
|
|
def update_settings(
|
|
payload: schemas.SettingsUpdate,
|
|
db: Session = Depends(get_db),
|
|
user: models.User = Depends(auth.get_current_user),
|
|
):
|
|
settings = get_settings(db, user)
|
|
fields = payload.model_dump(exclude_unset=True)
|
|
# Write-only API key: absent = unchanged, "" = cleared, else encrypted.
|
|
if "api_key" in fields:
|
|
fields["api_key"] = security.encrypt_secret(fields["api_key"].strip())
|
|
embedding_model_changed = (
|
|
"embedding_model" in fields
|
|
and fields["embedding_model"] != settings.embedding_model
|
|
)
|
|
for field, value in fields.items():
|
|
setattr(settings, field, value)
|
|
if embedding_model_changed:
|
|
# Vectors from the old model have a different dimensionality/space;
|
|
# clear them so the post-turn task re-embeds with the new model.
|
|
# (This user's adventures only — settings are per-user now.)
|
|
owned = (
|
|
db.query(models.Adventure.id)
|
|
.filter(models.Adventure.user_id == user.id)
|
|
.scalar_subquery()
|
|
)
|
|
db.query(models.Memory).filter(models.Memory.adventure_id.in_(owned)).update(
|
|
{"embedding": None}, synchronize_session=False
|
|
)
|
|
db.commit()
|
|
return settings
|
|
|
|
|
|
async def list_endpoint_models(cfg: auth.ProviderConfig) -> dict:
|
|
"""GET the endpoint's /models listing. Doubles as a connectivity check, so
|
|
failures come back as {"ok": False, "detail": ...} rather than raising."""
|
|
url = cfg.endpoint_url.rstrip("/") + "/models"
|
|
headers = {}
|
|
if cfg.api_key:
|
|
headers["Authorization"] = f"Bearer {cfg.api_key}"
|
|
try:
|
|
async with httpx.AsyncClient(timeout=10) as client:
|
|
resp = await client.get(url, headers=headers)
|
|
except httpx.HTTPError as exc:
|
|
return {"ok": False, "detail": f"Connection failed: {exc}"}
|
|
|
|
if resp.status_code != 200:
|
|
return {"ok": False, "detail": f"HTTP {resp.status_code}: {resp.text[:300]}"}
|
|
|
|
models_available: list[str] = []
|
|
try:
|
|
data = resp.json()
|
|
models_available = [m.get("id", "?") for m in data.get("data", [])]
|
|
except (ValueError, AttributeError, TypeError):
|
|
pass # non-JSON or unexpected shape — connectivity is still confirmed
|
|
return {"ok": True, "models": models_available}
|
|
|
|
|
|
@router.post("/test")
|
|
async def test_connection(
|
|
request: Request,
|
|
db: Session = Depends(get_db),
|
|
user: models.User = Depends(auth.get_current_user),
|
|
):
|
|
"""Cheap connectivity check against whatever the turn engine would actually
|
|
use — including the shared demo endpoint when the user has no key."""
|
|
limits.rate_limit("connection-test", request, user)
|
|
settings = get_settings(db, user)
|
|
return await list_endpoint_models(auth.resolve_provider_config(settings))
|