mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-31 14:47:13 +00:00
feat(tenancy): add Workspace multi-tenant foundation (#2353)
* Document multi-tenant workspace architecture * Add OSS and commercial workspace boundaries * docs: redesign multi-tenant workspace architecture * feat(tenancy): implement workspace isolation * docs(tenancy): record verification evidence * docs(tenancy): revise single-instance SaaS topology * docs(tenancy): refine architecture options * docs: finalize cloud v2 multi-tenant decisions * feat(tenancy): establish cloud isolation foundations * feat(tenancy): harden shared cloud runtime boundaries * docs(tenancy): record final isolation verification * fix(tenancy): close isolation and permission gaps * docs(tenancy): record final isolation verification * feat(tenancy): connect cloud workspace control plane * fix(build): install git for pinned SDK * docs(cloud): update control plane verification * chore: update multi-tenant SDK pin * fix(cloud): skip legacy model sync during startup * test(cloud): preserve minimal model manager fixtures * fix(cloud): preserve authenticated account context * fix(cloud): reuse authenticated account for user info * feat(cloud): complete Workspace settings navigation * test(web): cover Workspace dropdown menu * feat(web): place workspace controls in sidebar * refactor(web): streamline workspace controls * style(web): format workspace layout test * fix(cloud): surface runtime and workspace plan status * fix(plugin): keep runtime identity stable across restarts * fix(ui): widen and center workspace switcher * fix(ui): hide roles from workspace switcher * fix(ui): align workspace switcher with sidebar entries * feat(workspace): add in-product collaboration and direct Cloud launch * style: format collaboration changes * fix(workspace): bind collaboration APIs to tenant UoW * fix(cloud): preserve Core-owned collaboration state * test(cloud): require Space identity for invite registration * feat(cloud): complete secure invitation experience * style(web): format invitation flows * fix(cloud): recover box runtime without unscoped skill reload * feat(oss): enforce invitation account and owner billing flows * style: format OSS account service * test(oss): cover invitation logout handoff * fix(oss): resolve workspace owner in scoped session * feat(cloud): harden multi-tenant runtime resources * fix(cloud): bound runtime restart storms * fix(cloud): eliminate periodic runtime CPU spikes * fix(cloud): enforce instance capacity ceilings * fix(cloud): scope public login capability discovery * fix(cloud): bound tenant maintenance and monitoring work * fix(runtime): bound tenant resource amplification * fix(deps): pin green multi-tenant plugin SDK * fix(cloud): handle unavailable skill capability * fix(security): require authentication for image file endpoint (H-2) - Changed /api/v1/files/image from AuthType.NONE to USER_TOKEN_OR_API_KEY - Added Permission.RESOURCE_VIEW requirement - Prevents unauthenticated cross-tenant file access via leaked keys - Fixes HIGH severity finding from multi-tenant security review docs: add comprehensive database migration guide - Complete migration steps for OSS → multi-tenant - Backup, execution, verification procedures - Rollback scenarios and recovery plans - Performance tuning recommendations * test: add comprehensive cross-tenant isolation tests Added 7 critical test scenarios for multi-tenant boundaries: - Cross-tenant bot access prevention - Viewer role read-only enforcement - Removed member immediate access revocation - Model provider credential isolation - WebSocket message isolation - Invitation token workspace scoping - Multi-workspace context validation These tests address P0-2 coverage gaps for: - workspaces.py (membership & invitation flows) - user.py (authentication & authorization) - websocket_chat.py (real-time isolation) - plugins.py (resource access control) docs: finalize database migration guide * fix(security): resolve M-1, M-2, M-3 security findings M-1: WebSocket authorization TOCTOU race (FIXED) - Changed _revalidate_websocket_authorization to return RequestContext - Ensures validated context is used immediately without race window - Prevents removed members from sending messages during revalidation gap M-2: Model Manager cache workspace isolation (VERIFIED) - Confirmed _CacheKey already uses 4-tuple: (instance, workspace, generation, resource) - Cache is properly scoped per workspace, no cross-tenant leakage possible - No code change needed, documented as working correctly M-3: Invitation lock workspace scoping (FIXED) - Changed lock key from token_digest to workspace_uuid:token_digest - Prevents DoS where attacker locks token in Workspace A to block Workspace B - Locks now isolated per workspace All MEDIUM severity findings from security review now resolved. * fix(cloud): unblock tenant CI and enforce knowledge quotas * fix(tenancy): scope rerank model sync --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>
This commit is contained in:
RockChinQ
@@ -0,0 +1,177 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import time
|
||||
from collections.abc import Sequence
|
||||
|
||||
import regex
|
||||
|
||||
|
||||
MAX_PATTERN_COUNT = 64
|
||||
MAX_PATTERN_CHARS = 1024
|
||||
MAX_INPUT_CHARS = 1024 * 1024
|
||||
MAX_REPLACEMENT_CHARS = 64
|
||||
MAX_MASKED_OUTPUT_CHARS = 2 * 1024 * 1024
|
||||
DEFAULT_OPERATION_TIMEOUT_SECONDS = 0.05
|
||||
|
||||
|
||||
class SafeRegexError(ValueError):
|
||||
"""Base class for rejected, invalid, or timed-out tenant regex work."""
|
||||
|
||||
|
||||
class SafeRegexLimitError(SafeRegexError):
|
||||
"""Raised when a regex operation exceeds a deterministic resource limit."""
|
||||
|
||||
|
||||
class SafeRegexTimeoutError(SafeRegexError):
|
||||
"""Raised when the regex engine exhausts the operation CPU budget."""
|
||||
|
||||
|
||||
def _validate_patterns(patterns: Sequence[str]) -> tuple[str, ...]:
|
||||
normalized = tuple(patterns)
|
||||
if len(normalized) > MAX_PATTERN_COUNT:
|
||||
raise SafeRegexLimitError(f'At most {MAX_PATTERN_COUNT} regex patterns are allowed')
|
||||
for pattern in normalized:
|
||||
if not isinstance(pattern, str):
|
||||
raise SafeRegexError('Regex patterns must be strings')
|
||||
if len(pattern) > MAX_PATTERN_CHARS:
|
||||
raise SafeRegexLimitError(f'Regex patterns may contain at most {MAX_PATTERN_CHARS} characters')
|
||||
return normalized
|
||||
|
||||
|
||||
def _validate_input(value: str) -> None:
|
||||
if not isinstance(value, str):
|
||||
raise SafeRegexError('Regex input must be a string')
|
||||
if len(value) > MAX_INPUT_CHARS:
|
||||
raise SafeRegexLimitError(f'Regex input may contain at most {MAX_INPUT_CHARS} characters')
|
||||
|
||||
|
||||
def _remaining_seconds(deadline: float) -> float:
|
||||
remaining = deadline - time.monotonic()
|
||||
if remaining <= 0:
|
||||
raise SafeRegexTimeoutError('Regex operation timed out')
|
||||
return remaining
|
||||
|
||||
|
||||
def _compile(pattern: str):
|
||||
try:
|
||||
return regex.compile(pattern)
|
||||
except regex.error as exc:
|
||||
raise SafeRegexError(f'Invalid regex: {exc}') from exc
|
||||
|
||||
|
||||
def _matches_any_sync(
|
||||
patterns: Sequence[str],
|
||||
value: str,
|
||||
*,
|
||||
mode: str,
|
||||
timeout_seconds: float,
|
||||
) -> bool:
|
||||
normalized_patterns = _validate_patterns(patterns)
|
||||
_validate_input(value)
|
||||
if mode not in {'match', 'search'}:
|
||||
raise ValueError(f'Unsupported safe regex mode: {mode}')
|
||||
|
||||
deadline = time.monotonic() + timeout_seconds
|
||||
try:
|
||||
for pattern in normalized_patterns:
|
||||
compiled = _compile(pattern)
|
||||
matcher = compiled.match if mode == 'match' else compiled.search
|
||||
if matcher(
|
||||
value,
|
||||
timeout=_remaining_seconds(deadline),
|
||||
concurrent=True,
|
||||
):
|
||||
return True
|
||||
except TimeoutError as exc:
|
||||
raise SafeRegexTimeoutError('Regex operation timed out') from exc
|
||||
return False
|
||||
|
||||
|
||||
async def matches_any(
|
||||
patterns: Sequence[str],
|
||||
value: str,
|
||||
*,
|
||||
mode: str = 'search',
|
||||
timeout_seconds: float = DEFAULT_OPERATION_TIMEOUT_SECONDS,
|
||||
) -> bool:
|
||||
"""Match untrusted patterns without blocking the shared event loop."""
|
||||
|
||||
if timeout_seconds <= 0:
|
||||
raise ValueError('timeout_seconds must be positive')
|
||||
return await asyncio.to_thread(
|
||||
_matches_any_sync,
|
||||
patterns,
|
||||
value,
|
||||
mode=mode,
|
||||
timeout_seconds=timeout_seconds,
|
||||
)
|
||||
|
||||
|
||||
def _mask_patterns_sync(
|
||||
patterns: Sequence[str],
|
||||
value: str,
|
||||
*,
|
||||
mask: str,
|
||||
mask_word: str,
|
||||
timeout_seconds: float,
|
||||
) -> tuple[bool, str]:
|
||||
normalized_patterns = _validate_patterns(patterns)
|
||||
_validate_input(value)
|
||||
if len(mask) > MAX_REPLACEMENT_CHARS or len(mask_word) > MAX_REPLACEMENT_CHARS:
|
||||
raise SafeRegexLimitError(f'Regex replacements may contain at most {MAX_REPLACEMENT_CHARS} characters')
|
||||
|
||||
# Reject amplification before invoking a replacement callback. This is
|
||||
# deliberately conservative: a hostile replacement must not allocate tens
|
||||
# of megabytes before the post-operation output check can run.
|
||||
replacement_width = len(mask_word) if mask_word else len(mask)
|
||||
if replacement_width * max(1, len(value)) > MAX_MASKED_OUTPUT_CHARS:
|
||||
raise SafeRegexLimitError('Regex replacement could exceed the masked output limit')
|
||||
|
||||
deadline = time.monotonic() + timeout_seconds
|
||||
found = False
|
||||
current = value
|
||||
|
||||
def replace(match) -> str:
|
||||
nonlocal found
|
||||
found = True
|
||||
if mask_word:
|
||||
return mask_word
|
||||
return mask * len(match.group(0))
|
||||
|
||||
try:
|
||||
for pattern in normalized_patterns:
|
||||
compiled = _compile(pattern)
|
||||
current = compiled.sub(
|
||||
replace,
|
||||
current,
|
||||
timeout=_remaining_seconds(deadline),
|
||||
concurrent=True,
|
||||
)
|
||||
if len(current) > MAX_MASKED_OUTPUT_CHARS:
|
||||
raise SafeRegexLimitError('Regex replacement exceeded the masked output limit')
|
||||
except TimeoutError as exc:
|
||||
raise SafeRegexTimeoutError('Regex operation timed out') from exc
|
||||
return found, current
|
||||
|
||||
|
||||
async def mask_patterns(
|
||||
patterns: Sequence[str],
|
||||
value: str,
|
||||
*,
|
||||
mask: str,
|
||||
mask_word: str,
|
||||
timeout_seconds: float = DEFAULT_OPERATION_TIMEOUT_SECONDS,
|
||||
) -> tuple[bool, str]:
|
||||
"""Apply untrusted masking patterns with bounded CPU and output growth."""
|
||||
|
||||
if timeout_seconds <= 0:
|
||||
raise ValueError('timeout_seconds must be positive')
|
||||
return await asyncio.to_thread(
|
||||
_mask_patterns_sync,
|
||||
patterns,
|
||||
value,
|
||||
mask=mask,
|
||||
mask_word=mask_word,
|
||||
timeout_seconds=timeout_seconds,
|
||||
)
|
||||
Reference in New Issue
Block a user