Files
chat_backend/llm_be/chat_backend/serializers.py
T
westfarn d54094f5e0
Unit Tests / test (push) Successful in 10s
Deploy Beta / unit-tests (push) Successful in 10s
Deploy Beta / docker (push) Successful in 21s
Deploy Beta / deploy-beta (push) Successful in 40s
Tier-gated RAG + Drive document sources (#42) (#54)
## Summary

Implements epic [#42](#42) (children #43–#53) and advances [#11](#11).

- **Entitlement:** `allows_rag` on plans (founders / backer / pro / business; not standard); exposed as `features.rag`
- **Gates:** document REST + WS `PromptType.RAG` use `assert_feature_allowed(..., "rag")`
- **Lifecycle:** dedupe ingest, delete vectors by `document_id`, honor `active`, fix document detail PATCH/DELETE
- **Workspaces:** auto-create default company workspace; fail-closed scoping
- **Drive:** personal + company Google/Microsoft connect (`link_drive` / `link_company_drive`), resource selection, sync, webhooks stubs, `sync_drive_connections` management command
- **Docs/env:** README + `.env*.example` updated

Companion FE: `chat_web_app` branch `feature/rag-epic-42-ui` (#81–#85).

## Test plan

- [x] `SKIP_RAG_INIT=1 uv run python manage.py test` (457 OK)
- [ ] Migrate finance `0004` + chat_backend `0028` on beta
- [ ] Verify Standard user: Documents API 403 + no RAG retrieval
- [ ] Verify Founders/Pro: upload + list + active toggle
- [ ] Connect Google/Microsoft Drive (incremental scopes) and Sync
- [ ] Company manager: `link_company_drive`; non-manager 403
- [ ] Run `manage.py sync_drive_connections`Reviewed-on: #54
2026-08-01 14:02:36 -07:00

317 lines
9.3 KiB
Python

from rest_framework_simplejwt.serializers import TokenObtainPairSerializer
from rest_framework import serializers
from django.db.models import Count, Q, Sum
from .models import (
CustomUser,
Announcement,
Company,
Conversation,
Prompt,
PromptMetric,
Feedback,
FEEDBACK_CATEGORIES,
DocumentWorkspace,
Document,
DriveConnection,
)
class MyTokenObtainPairSerializer(TokenObtainPairSerializer):
@classmethod
def get_token(cls, user):
token = super(MyTokenObtainPairSerializer, cls).get_token(user)
# add custom claim
token["company"] = "something here"
return token
def validate(self, attrs):
data = super().validate(attrs)
if getattr(self.user, "deleted", False):
from rest_framework_simplejwt.exceptions import AuthenticationFailed
raise AuthenticationFailed(
"No active account found with the given credentials",
code="no_active_account",
)
return data
class CompanySerializer(serializers.ModelSerializer):
class Meta:
model = Company
fields = "__all__"
class AnnouncmentSerializer(serializers.ModelSerializer):
class Meta:
model = Announcement
fields = "__all__"
class FeedbackSerializer(serializers.ModelSerializer):
class Meta:
model = Feedback
fields = "__all__"
class CustomUserSerializer(serializers.ModelSerializer):
email = serializers.EmailField(required=True)
username = serializers.CharField()
password = serializers.CharField(min_length=8, write_only=True)
company = CompanySerializer()
has_usable_password = serializers.BooleanField()
subscription = serializers.SerializerMethodField()
class Meta:
model = CustomUser
fields = "__all__"
extra_kwargs = {"password": {"write_only": True}}
def get_subscription(self, obj):
from finance.services.plans import needs_checkout, plan_to_dict
from finance.models import UserSubscription
try:
sub = obj.subscription
except UserSubscription.DoesNotExist:
return {
"plan": None,
"status": UserSubscription.Status.NONE,
"source": UserSubscription.Source.NONE,
"needs_checkout": True,
"cancel_at_period_end": False,
"current_period_end": None,
}
return {
"plan": plan_to_dict(sub.plan) if sub.plan_id else None,
"status": sub.status,
"source": sub.source,
"needs_checkout": needs_checkout(obj),
"cancel_at_period_end": bool(sub.cancel_at_period_end),
"current_period_end": (
sub.current_period_end.isoformat() if sub.current_period_end else None
),
}
class SelfServeRegistrationSerializer(serializers.Serializer):
"""Minimal payload for public self-serve sign-up (gated by settings)."""
email = serializers.EmailField(required=True)
password = serializers.CharField(min_length=8, write_only=True)
first_name = serializers.CharField(
required=False, allow_blank=True, max_length=150, default=""
)
last_name = serializers.CharField(
required=False, allow_blank=True, max_length=150, default=""
)
company_name = serializers.CharField(
required=False, allow_blank=True, max_length=256, default=""
)
def validate_email(self, value: str) -> str:
email = value.strip().lower()
if CustomUser.objects.filter(email__iexact=email).exists():
raise serializers.ValidationError("A user with this email already exists.")
if CustomUser.objects.filter(username__iexact=email).exists():
raise serializers.ValidationError("A user with this email already exists.")
return email
def create(self, validated_data):
from finance.services.plans import try_redeem_backer_email
email = validated_data["email"]
password = validated_data["password"]
first_name = (validated_data.get("first_name") or "").strip()
last_name = (validated_data.get("last_name") or "").strip()
company_name = (validated_data.get("company_name") or "").strip()
if not company_name:
company_name = f"{email}'s workspace"
company = Company.objects.create(
name=company_name,
state="NA",
zipcode="00000",
address="N/A",
)
user = CustomUser.objects.create_user(
username=email,
email=email,
password=password,
first_name=first_name,
last_name=last_name,
company=company,
is_company_manager=True,
)
try_redeem_backer_email(user)
return user
def _conversation_token_totals(conversation_id: int):
"""
Sum PromptMetric tokens for a conversation.
Returns nulls when the provider never reported usage (never fabricate 0).
"""
agg = PromptMetric.objects.filter(conversation_id=conversation_id).aggregate(
tin=Sum("tokens_in"),
tout=Sum("tokens_out"),
with_in=Count("id", filter=Q(tokens_in__isnull=False)),
with_out=Count("id", filter=Q(tokens_out__isnull=False)),
)
return (
agg["tin"] if agg["with_in"] else None,
agg["tout"] if agg["with_out"] else None,
)
def _prompt_token_pair(prompt_id: int):
metric = (
PromptMetric.objects.filter(prompt_id=prompt_id)
.order_by("-created")
.only("tokens_in", "tokens_out")
.first()
)
if metric is None:
return None, None
return metric.tokens_in, metric.tokens_out
class ConversationSerializer(serializers.ModelSerializer):
tokens_in = serializers.SerializerMethodField()
tokens_out = serializers.SerializerMethodField()
class Meta:
model = Conversation
fields = (
"title",
"created",
"last_modified",
"id",
"tokens_in",
"tokens_out",
)
def _token_pair(self, obj):
cache = self.context.setdefault("_conversation_token_cache", {})
if obj.id not in cache:
cache[obj.id] = _conversation_token_totals(obj.id)
return cache[obj.id]
def get_tokens_in(self, obj):
tin, _ = self._token_pair(obj)
return tin
def get_tokens_out(self, obj):
_, tout = self._token_pair(obj)
return tout
class PromptSerializer(serializers.ModelSerializer):
tokens_in = serializers.SerializerMethodField()
tokens_out = serializers.SerializerMethodField()
class Meta:
model = Prompt
fields = (
"message",
"user_created",
"created",
"id",
"tokens_in",
"tokens_out",
)
def _token_pair(self, obj):
cache = self.context.setdefault("_prompt_token_cache", {})
if obj.id not in cache:
cache[obj.id] = _prompt_token_pair(obj.id)
return cache[obj.id]
def get_tokens_in(self, obj):
tin, _ = self._token_pair(obj)
return tin
def get_tokens_out(self, obj):
_, tout = self._token_pair(obj)
return tout
def validate_message(self, value: str) -> str:
if value is None or not str(value).strip():
raise serializers.ValidationError("Message text cannot be empty.")
return str(value).strip()
class BasicUserSerializer(serializers.ModelSerializer):
class Meta:
model = CustomUser
fields = (
"email",
"first_name",
"last_name",
"is_active",
"has_usable_password",
"is_company_manager",
"has_signed_tos",
)
# document serializers
class DocumentWorkspaceSerializer(serializers.ModelSerializer):
class Meta:
model = DocumentWorkspace
fields = ["id", "name", "created"]
read_only_fields = ["id", "created"]
class DocumentSerializer(serializers.ModelSerializer):
class Meta:
model = Document
fields = [
"id",
"workspace",
"file",
"uploaded_at",
"processed",
"created",
"active",
]
read_only_fields = ["id", "uploaded_at", "processed", "created"]
# drive connection serializers (#47-#52)
class DriveConnectionSerializer(serializers.ModelSerializer):
"""Never exposes access_token/refresh_token to the client."""
class Meta:
model = DriveConnection
fields = [
"id",
"provider",
"kind",
"external_account_email",
"selected_resource_ids",
"selected_resource_labels",
"last_sync_at",
"last_sync_status",
"last_sync_error",
"is_active",
"created",
]
read_only_fields = fields
class DriveConnectionResourcesSerializer(serializers.Serializer):
resource_ids = serializers.ListField(
child=serializers.CharField(max_length=512), allow_empty=True
)
resource_labels = serializers.ListField(
child=serializers.CharField(max_length=512, allow_blank=True),
allow_empty=True,
required=False,
default=list,
)