Files
kite/backend/api/cloud/schemas.py
T
curo1305 a0d5c1d6c4 feat(14.1-02): CloudItemDetailOut schema + resolve_owned_cloud_item_detail + GET detail route
- Add CloudItemDetailOut allowlist schema to backend/api/cloud/schemas.py
  (excludes credentials_enc, object_key, version_key, raw provider URLs — T-14.1-03)
- Add CloudItemDetail dataclass and resolve_owned_cloud_item_detail service helper
  to backend/services/cloud_items.py (owner-scoped, metadata-only, no byte hydration)
- Add GET /connections/{id}/items/{item_id:path}/detail route to operations.py
  with get_regular_user (admin 403), ConnectionNotFound → 404, CloudItemNotFound → 404
- All 8 test_cloud_detail_parity tests now pass (D-05, D-07, D-16, T-14.1-03/04/06)
2026-06-26 21:54:28 +02:00

472 lines
18 KiB
Python

"""
Whitelisted Pydantic response schemas for the cloud API package.
All schemas are explicit allowlists — credentials_enc, tokens, and passwords
are deliberately absent. T-12-03: credential exclusion by design.
Phase 13 additions:
- ConnectionHealthOut: typed health status response (D-12, CONN-03)
- ReconnectOut: typed reconnect response (CONN-01..03)
- ContentResultOut: typed open/preview/download response (D-02, D-18, T-13-14)
- MutationResultOut: typed kind/reason mutation response (D-05..11)
Phase 14 additions:
- CacheStatusOut: aggregate cache usage + settings response (T-14-02, T-14-08)
- CacheSettingsUpdateRequest: PATCH body for updating analysis settings/cache limit
Phase 14.1 additions:
- CloudItemDetailOut: owner-scoped cloud item detail with analysis fields (D-05)
- force field on AnalysisEnqueueRequest: bypass already_current check (D-11)
"""
from __future__ import annotations
from datetime import datetime
from typing import List, Optional
from pydantic import BaseModel, Field, field_validator
# ── Phase 14.1 cloud item detail schema ──────────────────────────────────────
class CloudItemDetailOut(BaseModel):
"""Owner-scoped cloud item detail with analysis fields and source metadata.
Strict allowlist: object_key, credentials_enc, version_key, and raw provider
URLs are absent by design (T-14.1-03, mirrors CacheStatusOut T-14-02 pattern).
Fields:
id: DocuVault stable UUID (str).
provider_item_id: Provider-side opaque item identifier.
name: File or folder name.
kind: "file" | "folder".
parent_ref: Provider parent reference (opaque string, no URL).
content_type: MIME type from provider metadata.
size: Provider-reported byte count (provider_size).
modified_at: Provider-reported last modification timestamp.
etag: Provider entity tag for version comparison.
provider: Connection provider string (e.g. "google_drive").
display_name: Human-readable connection display name.
location: Human path (path_snapshot) or parent_ref — no provider URL.
analysis_status: "pending" | "indexed" | "stale" | "failed" | ...
semantic_index_status: "none" | "indexed" | ...
extracted_text: Text extracted during analysis (None when not yet analyzed).
topics: List of topic names linked to this item (empty when not analyzed).
capabilities: Per-action capability map (action → CloudCapabilityOut).
unsupported_analysis_reason: Reason why analysis is unsupported (None when supported).
is_stale: True when analysis_status == "stale" (D-07 convenience flag).
"""
# Core identity (no object_key, credentials_enc, version_key — T-14.1-03)
id: str
provider_item_id: str
name: str
kind: str
parent_ref: Optional[str] = None
# Provider metadata
content_type: Optional[str] = None
size: Optional[int] = None
modified_at: Optional[datetime] = None
etag: Optional[str] = None
# Connection source metadata (D-04) — no raw provider URLs
provider: str
display_name: str
location: Optional[str] = None # path_snapshot or parent_ref, never a provider URL
# Analysis fields (D-05, D-07, D-08)
analysis_status: str = "pending"
semantic_index_status: str = "none"
extracted_text: Optional[str] = None
topics: List[str] = []
# Action availability (D-05, D-16)
capabilities: dict[str, CloudCapabilityOut] = {}
unsupported_analysis_reason: Optional[str] = None # populated when analyze is unsupported
is_stale: bool = False # True when analysis_status == "stale" (D-07)
# ── Capability / item schemas ─────────────────────────────────────────────────
class CloudCapabilityOut(BaseModel):
"""Whitelisted capability descriptor. reason/message only when not supported."""
action: str
state: str # "supported" | "unsupported" | "temporarily_unavailable"
reason: Optional[str] = None
message: Optional[str] = None
class CloudItemOut(BaseModel):
"""Normalized cloud item metadata. No credentials or byte content."""
id: str # DocuVault stable UUID
provider_item_id: str
name: str
kind: str # "file" | "folder"
parent_ref: Optional[str] = None
content_type: Optional[str] = None
size: Optional[int] = None
modified_at: Optional[datetime] = None
etag: Optional[str] = None
capabilities: dict[str, CloudCapabilityOut] = {}
# ── Freshness / folder state schemas ─────────────────────────────────────────
class FolderFreshnessOut(BaseModel):
"""Freshness and error state for a browsed folder."""
refresh_state: str # "fresh" | "refreshing" | "warning"
last_refreshed_at: Optional[datetime] = None
error_code: Optional[str] = None
error_message: Optional[str] = None
# ── Browse response ───────────────────────────────────────────────────────────
class CloudBrowseResponse(BaseModel):
"""Owner-scoped connection-ID browse response.
T-12-01: items are always scoped to the resolved connection which is owned
by the requesting user. credentials_enc is never included.
"""
connection_id: str
provider: str
display_name: str
parent_ref: Optional[str]
items: List[CloudItemOut]
capabilities: dict[str, CloudCapabilityOut]
freshness: FolderFreshnessOut
# ── Connection schemas ────────────────────────────────────────────────────────
class ConnectionRenameRequest(BaseModel):
"""Validated PATCH body for renaming a connection display name.
Only display_name is accepted — mass assignment prevention.
"""
display_name: str = Field(..., max_length=255)
@field_validator("display_name")
@classmethod
def must_be_nonblank(cls, v: str) -> str:
stripped = v.strip()
if not stripped:
raise ValueError("display_name must not be blank")
return stripped
# ── Phase 13 health / reconnect schemas ────────────────────────────────────────
class ConnectionHealthOut(BaseModel):
"""Typed connection health response.
D-12: Explicit health status available without probing on every browse.
CONN-03: Never exposes credentials_enc, tokens, or raw provider URLs.
status: 'healthy' | 'degraded' | 'auth_failed' | 'offline'
"""
status: str
connection_id: str
provider: str
display_name: Optional[str] = None
class ReconnectOut(BaseModel):
"""Typed reconnect result.
CONN-01: No new connection row created (reconnected patches in place).
CONN-02: credentials_enc updated with re-encrypted token.
CONN-03: No credentials, tokens, or provider URLs in response.
D-14: Cached metadata preserved as stale.
"""
status: str
connection_id: str
provider: str
display_name: Optional[str] = None
reconnected: bool = True
# ── Phase 13 content result schemas ───────────────────────────────────────────
class ContentResultOut(BaseModel):
"""Typed open/preview result body.
D-02: Provider credentials and raw provider URLs must never appear in responses.
D-18: Preview is binary-only; unsupported formats fall back to download fallback.
T-13-14: Stable kind/reason codes let the frontend route without parsing provider payloads.
kind: 'open' | 'preview' | 'download' | 'unsupported_preview'
reason: discriminator code (e.g. 'binary_supported', 'unsupported_format', 'authorized')
url: DocuVault-scoped authorized URL (never a raw provider URL)
"""
kind: str
reason: Optional[str] = None
url: Optional[str] = None
content_type: Optional[str] = None
# ── Phase 13 mutation result schemas ──────────────────────────────────────────
class MutationResultOut(BaseModel):
"""Typed mutation result body used by rename, move, delete, and create-folder.
T-13-14: Stable kind/reason codes let the frontend route without parsing
raw provider error payloads.
kind: 'renamed' | 'moved' | 'deleted' | 'folder' | 'conflict' | 'stale' |
'offline' | 'reauth_required' | 'invalid_destination' | 'unsupported_operation'
reason: discriminator detail (e.g. 'trashed', 'permanent', 'name_collision',
'item_changed', 'provider_unreachable', 'token_expired',
'self_destination', 'cross_connection', 'provider_unsupported')
"""
kind: str
reason: Optional[str] = None
name: Optional[str] = None
provider_item_id: Optional[str] = None
parent_ref: Optional[str] = None
# ── Phase 13 mutation request schemas ─────────────────────────────────────────
class CreateFolderRequest(BaseModel):
"""Request body for POST /connections/{id}/folders."""
parent_ref: Optional[str] = None
name: str = Field(..., max_length=255)
@field_validator("name")
@classmethod
def must_be_nonblank(cls, v: str) -> str:
stripped = v.strip()
if not stripped:
raise ValueError("name must not be blank")
return stripped
class RenameItemRequest(BaseModel):
"""Request body for PATCH /connections/{id}/items/{item_id}/rename."""
new_name: str = Field(..., max_length=255)
etag: Optional[str] = None
@field_validator("new_name")
@classmethod
def must_be_nonblank(cls, v: str) -> str:
stripped = v.strip()
if not stripped:
raise ValueError("new_name must not be blank")
return stripped
class MoveItemRequest(BaseModel):
"""Request body for POST /connections/{id}/items/{item_id}/move."""
destination_parent_ref: str
destination_connection_id: Optional[str] = None
etag: Optional[str] = None
# ── Phase 14 cache schemas ─────────────────────────────────────────────────────
class CacheStatusOut(BaseModel):
"""Aggregate cache usage and user analysis settings.
T-14-02: object_key, credentials_enc, and raw provider URLs are absent by
design. This schema is a strict allowlist — no internal MinIO keys or
credentials can leak through it.
entry_count: Number of active (non-evicted) cache entries.
total_bytes: Sum of size_bytes across active entries.
cache_limit_bytes: User's preferred cache byte ceiling.
tier_cap_bytes: Maximum allowed cache limit for this tier.
analysis_progress_detail: "simple" | "detailed" — default "simple".
analysis_failure_behavior:"pause_batch" | "continue_item" — default "pause_batch".
"""
entry_count: int = 0
total_bytes: int = 0
cache_limit_bytes: int
tier_cap_bytes: int
analysis_progress_detail: str
analysis_failure_behavior: str
class CacheSettingsUpdateRequest(BaseModel):
"""PATCH body for updating analysis preferences and cache limit.
Only provided (non-None) fields are applied. Enum validation and bounds
checking are performed in the service layer.
Mass-assignment prevention: only the three fields below are accepted.
"""
analysis_progress_detail: Optional[str] = Field(
default=None,
description="Progress label verbosity: 'simple' or 'detailed'",
)
analysis_failure_behavior: Optional[str] = Field(
default=None,
description="Batch failure mode: 'pause_batch' or 'continue_item'",
)
cloud_cache_limit_bytes: Optional[int] = Field(
default=None,
ge=1,
description="Preferred byte ceiling for the local byte cache",
)
# ── Phase 14 analysis request schemas ─────────────────────────────────────────
class AnalysisEstimateRequest(BaseModel):
"""Request body for POST /analysis/connections/{id}/estimate.
scope: "file" | "selection" | "folder" | "connection"
provider_item_ids: Required for file/selection/folder scope. Omitted for connection scope.
recursive: Expand folder subtree recursively (folder scope only; connection always recursive).
"""
scope: str = Field(..., description="file | selection | folder | connection")
provider_item_ids: Optional[List[str]] = Field(
default=None,
description="Provider item IDs for file/selection/folder scope",
)
recursive: bool = Field(
default=False,
description="Expand folder children recursively (folder scope)",
)
class AnalysisEnqueueRequest(BaseModel):
"""Request body for POST /analysis/connections/{id}/jobs.
scope: "file" | "selection" | "folder" | "connection"
provider_item_ids: Required for file/selection/folder scope.
recursive: Expand folder subtree recursively.
failure_behavior: "pause_batch" (default) | "continue_item" (D-11).
force: When True, bypass already_current check and re-queue indexed items (D-11).
"""
scope: str = Field(..., description="file | selection | folder | connection")
provider_item_ids: Optional[List[str]] = Field(default=None)
recursive: bool = Field(default=False)
failure_behavior: str = Field(
default="pause_batch",
description="pause_batch | continue_item",
)
force: bool = Field(
default=False,
description=(
"When True, bypass the already_current check and re-queue supported items "
"even if their version_key matches a prior indexed run. "
"Preserves existing idempotent behavior when False (default). "
"No provider mutation is performed regardless of this flag (ANALYZE-07)."
),
)
# ── Phase 14 analysis response schemas ────────────────────────────────────────
class AnalysisEstimateOut(BaseModel):
"""Estimate response — no credentials, bytes, or object_key (T-14-02).
supported_count: Files that can be analysed.
unsupported_count: Items that cannot be analysed (unsupported type, folder).
total_provider_bytes: Sum of provider_size across supported items.
recursive: Whether the estimate was recursive.
is_partial: True when metadata expansion was incomplete.
scope_kind: Echo of the requested scope.
"""
supported_count: int = 0
unsupported_count: int = 0
total_provider_bytes: int = 0
recursive: bool = False
is_partial: bool = False
scope_kind: str
class AnalysisJobOut(BaseModel):
"""Job status response — no credentials or object_key (T-14-02).
Exposes both simple and detailed aggregate counts. Caller requests detail
via ?detail=true query parameter.
Simple (default): waiting_count, working_count, done_count,
skipped_count, failed_count, total_count.
Detailed: queued_count, downloading_count, extracting_count,
classifying_count, indexed_count, already_current_count,
cancelled_count, failed_count, unsupported_count.
"""
job_id: str
connection_id: str
scope_kind: str
status: str
failure_behavior: str
recursive: bool = False
total_count: int = 0
# Simple labels (always present)
waiting_count: int = 0
working_count: int = 0
done_count: int = 0
skipped_count: int = 0
failed_count: int = 0
# Detailed labels (always present — 0 when detail=false, per-stage values when detail=true)
queued_count: int = 0
downloading_count: int = 0
extracting_count: int = 0
classifying_count: int = 0
indexed_count: int = 0
already_current_count: int = 0
cancelled_count: int = 0
unsupported_count: int = 0
created_at: Optional[datetime] = None
started_at: Optional[datetime] = None
finished_at: Optional[datetime] = None
class AnalysisEnqueueOut(BaseModel):
"""Enqueue response — returns a stable job_id for status polling (ANALYZE-01).
No credentials or object_key in response (T-14-02).
"""
job_id: str
status: str
total_count: int = 0
queued_count: int = 0
already_current_count: int = 0
unsupported_count: int = 0
class AnalysisJobItemOut(BaseModel):
"""Per-item job status — no credentials, object_key, or raw provider data (T-14-02)."""
id: str
cloud_item_id: str
provider_item_id: str
status: str
error_code: Optional[str] = None
error_message: Optional[str] = None
retry_count: int = 0
created_at: Optional[datetime] = None
finished_at: Optional[datetime] = None
class AnalysisControlOut(BaseModel):
"""Generic control result for cancel/skip/retry operations."""
kind: str # "cancelled" | "skipped" | "retried"
reason: Optional[str] = None
job_id: Optional[str] = None
item_id: Optional[str] = None