mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-09-16 14:57:15 +00:00
feat(provider): support Codex subscriptions with ChatGPT sign-in (#2513)
* feat(provider): support Codex subscriptions with ChatGPT sign-in * style: format Codex live integration test * fix(provider): preserve Codex identity in temporary model tests * fix(web): portal provider selector without dialog overflow * fix(web): allow native scrolling in provider dropdown * fix(provider): surface safe Codex quota and upstream errors * fix(web): provide reliable Codex copy feedback in dialogs * feat(provider): confirm cascade deletion from edit dialog * fix(persistence): discard connections after failed commit * fix(web): polish provider loading and confirmation motion --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>
This commit is contained in:
Hyu
@@ -15,6 +15,7 @@ from ....workspace.collaboration import MembershipPermissionError, WorkspaceColl
|
||||
from ....workspace.errors import WorkspaceNotFoundError
|
||||
from ....cloud.entitlements import EntitlementUnavailableError
|
||||
from ....core.errors import TaskCapacityError
|
||||
from ....provider.modelmgr.codex_errors import CodexProviderError
|
||||
from ..authz import (
|
||||
AuthenticationDeniedError,
|
||||
AuthorizationError,
|
||||
@@ -247,6 +248,8 @@ class RouterGroup(abc.ABC):
|
||||
return await f(*args, **kwargs)
|
||||
|
||||
except Exception as e: # 自动 500
|
||||
if isinstance(e, CodexProviderError):
|
||||
return self.http_status(e.status_code, e.error_code, str(e))
|
||||
if isinstance(e, AuthorizationError):
|
||||
return self.http_status(e.status_code, e.error_code, str(e))
|
||||
if isinstance(e, WorkspaceNotFoundError):
|
||||
|
||||
@@ -8,6 +8,80 @@ from ... import group
|
||||
@group.group_class('models/providers', '/api/v1/provider/providers')
|
||||
class ModelProvidersRouterGroup(group.RouterGroup):
|
||||
async def initialize(self) -> None:
|
||||
# Subscription authorization is an interactive, browser-user-only surface.
|
||||
@self.route(
|
||||
'/<provider_uuid>/codex/status',
|
||||
methods=['GET'],
|
||||
auth_type=group.AuthType.USER_TOKEN,
|
||||
permission=Permission.PROVIDER_SECRET_MANAGE,
|
||||
)
|
||||
async def codex_status(provider_uuid: str, request_context: RequestContext):
|
||||
try:
|
||||
return self.success(
|
||||
data=await self.ap.provider_service.codex_auth.status(request_context, provider_uuid)
|
||||
)
|
||||
except ValueError as exc:
|
||||
return self.http_status(400, -1, str(exc))
|
||||
|
||||
@self.route(
|
||||
'/<provider_uuid>/codex/device',
|
||||
methods=['POST'],
|
||||
auth_type=group.AuthType.USER_TOKEN,
|
||||
permission=Permission.PROVIDER_SECRET_MANAGE,
|
||||
)
|
||||
async def codex_device(provider_uuid: str, request_context: RequestContext):
|
||||
try:
|
||||
return self.success(
|
||||
data=await self.ap.provider_service.codex_auth.start(request_context, provider_uuid)
|
||||
)
|
||||
except ValueError as exc:
|
||||
return self.http_status(400, -1, str(exc))
|
||||
|
||||
@self.route(
|
||||
'/<provider_uuid>/codex/device/poll',
|
||||
methods=['POST'],
|
||||
auth_type=group.AuthType.USER_TOKEN,
|
||||
permission=Permission.PROVIDER_SECRET_MANAGE,
|
||||
)
|
||||
async def codex_poll(provider_uuid: str, request_context: RequestContext):
|
||||
body = await quart.request.get_json()
|
||||
if not isinstance(body, dict):
|
||||
return self.http_status(400, -1, 'JSON object required')
|
||||
try:
|
||||
return self.success(
|
||||
data=await self.ap.provider_service.codex_auth.poll(
|
||||
request_context, provider_uuid, body.get('authorization_id')
|
||||
)
|
||||
)
|
||||
except ValueError as exc:
|
||||
return self.http_status(400, -1, str(exc))
|
||||
|
||||
@self.route(
|
||||
'/<provider_uuid>/codex/auth',
|
||||
methods=['DELETE'],
|
||||
auth_type=group.AuthType.USER_TOKEN,
|
||||
permission=Permission.PROVIDER_SECRET_MANAGE,
|
||||
)
|
||||
async def codex_disconnect(provider_uuid: str, request_context: RequestContext):
|
||||
try:
|
||||
await self.ap.provider_service.codex_auth.disconnect(request_context, provider_uuid)
|
||||
return self.success()
|
||||
except ValueError as exc:
|
||||
return self.http_status(400, -1, str(exc))
|
||||
|
||||
@self.route(
|
||||
'/<provider_uuid>/codex/device/<authorization_id>',
|
||||
methods=['DELETE'],
|
||||
auth_type=group.AuthType.USER_TOKEN,
|
||||
permission=Permission.PROVIDER_SECRET_MANAGE,
|
||||
)
|
||||
async def codex_cancel(provider_uuid: str, authorization_id: str, request_context: RequestContext):
|
||||
try:
|
||||
await self.ap.provider_service.codex_auth.cancel(request_context, provider_uuid, authorization_id)
|
||||
return self.success()
|
||||
except ValueError as exc:
|
||||
return self.http_status(400, -1, str(exc))
|
||||
|
||||
@self.route(
|
||||
'',
|
||||
methods=['GET'],
|
||||
@@ -82,7 +156,15 @@ class ModelProvidersRouterGroup(group.RouterGroup):
|
||||
)
|
||||
async def _(provider_uuid: str, request_context: RequestContext) -> str:
|
||||
try:
|
||||
await self.ap.provider_service.delete_provider(request_context, provider_uuid)
|
||||
cascade_values = quart.request.args.getlist('cascade')
|
||||
if cascade_values:
|
||||
if len(cascade_values) != 1 or cascade_values[0] not in ('true', 'false'):
|
||||
return self.http_status(400, -1, 'cascade must be a single true or false value')
|
||||
await self.ap.provider_service.delete_provider(
|
||||
request_context, provider_uuid, cascade=cascade_values[0] == 'true'
|
||||
)
|
||||
else:
|
||||
await self.ap.provider_service.delete_provider(request_context, provider_uuid)
|
||||
return self.success()
|
||||
except ValueError as e:
|
||||
return self.http_status(400, -1, str(e))
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import uuid
|
||||
import traceback
|
||||
|
||||
@@ -7,8 +8,10 @@ import sqlalchemy
|
||||
|
||||
from ....cloud.model_catalog import LANGBOT_MODELS_PROVIDER_REQUESTER
|
||||
from ....core import app
|
||||
from ....core.task_boundary import create_detached_task
|
||||
from ....entity.persistence import model as persistence_model
|
||||
from ....workspace.errors import WorkspaceNotFoundError
|
||||
from ....provider.modelmgr.codex_auth import CodexAuth, REQUESTER as CODEX_REQUESTER, validate_config
|
||||
from .secrets import contains_secret_placeholder, redact_secrets, restore_secret_placeholders
|
||||
from .tenant import TenantContext, require_workspace_uuid, scope_statement
|
||||
|
||||
@@ -20,6 +23,8 @@ class ModelProviderService:
|
||||
|
||||
def __init__(self, ap: app.Application) -> None:
|
||||
self.ap = ap
|
||||
self.codex_auth = CodexAuth(ap)
|
||||
self._deletion_tasks: set[asyncio.Task[None]] = set()
|
||||
|
||||
def _is_cloud_runtime(self) -> bool:
|
||||
mode = getattr(self.ap.persistence_mgr, 'mode', None)
|
||||
@@ -116,14 +121,30 @@ class ModelProviderService:
|
||||
provider_data = provider_data.copy()
|
||||
if self._system_requester_is_reserved(provider_data.get('requester')):
|
||||
raise ValueError('space-chat-completions is reserved for the Cloud-managed LangBot Models provider')
|
||||
validate_config(provider_data)
|
||||
provider_data['uuid'] = str(uuid.uuid4())
|
||||
provider_data['workspace_uuid'] = require_workspace_uuid(context)
|
||||
provider_data['api_keys'] = self._normalize_api_keys(
|
||||
restore_secret_placeholders(provider_data.get('api_keys'), sensitive=True)
|
||||
)
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(persistence_model.ModelProvider).values(**provider_data)
|
||||
)
|
||||
if provider_data.get('requester') == CODEX_REQUESTER:
|
||||
async with self.ap.persistence_mgr.tenant_uow(provider_data['workspace_uuid']):
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(persistence_model.ModelProvider).values(**provider_data)
|
||||
)
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(persistence_model.CodexCredential).values(
|
||||
workspace_uuid=provider_data['workspace_uuid'],
|
||||
provider_uuid=provider_data['uuid'],
|
||||
payload={},
|
||||
version=0,
|
||||
lease_until=0,
|
||||
)
|
||||
)
|
||||
else:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(persistence_model.ModelProvider).values(**provider_data)
|
||||
)
|
||||
|
||||
# load to runtime
|
||||
runtime_provider = await self.ap.model_mgr.load_provider(context, provider_data)
|
||||
@@ -138,6 +159,17 @@ class ModelProviderService:
|
||||
raise ValueError('space-chat-completions is reserved for the Cloud-managed LangBot Models provider')
|
||||
provider_data.pop('uuid', None)
|
||||
provider_data.pop('workspace_uuid', None)
|
||||
if {'requester', 'base_url', 'api_keys'} & provider_data.keys():
|
||||
current = await self.get_provider(context, provider_uuid, include_secret=True)
|
||||
if current is None:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
if CODEX_REQUESTER in (current.get('requester'), provider_data.get('requester')):
|
||||
if provider_data.get('requester', current.get('requester')) != current.get('requester'):
|
||||
raise ValueError('Create a separate provider to change the ChatGPT authentication type')
|
||||
merged = {**current, **provider_data}
|
||||
validate_config(merged)
|
||||
provider_data['base_url'] = merged['base_url']
|
||||
provider_data['api_keys'] = []
|
||||
if 'api_keys' in provider_data:
|
||||
submitted_keys = provider_data.get('api_keys')
|
||||
if contains_secret_placeholder(submitted_keys, sensitive=True):
|
||||
@@ -163,60 +195,107 @@ class ModelProviderService:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
await self.ap.model_mgr.reload_provider(context, provider_uuid)
|
||||
|
||||
async def delete_provider(self, context: TenantContext, provider_uuid: str) -> None:
|
||||
"""Delete a provider (only if no models reference it)"""
|
||||
await self._assert_provider_mutable(context, provider_uuid)
|
||||
async def delete_provider(self, context: TenantContext, provider_uuid: str, cascade: bool = False) -> None:
|
||||
"""Delete a provider, optionally deleting all its Workspace-scoped models."""
|
||||
workspace_uuid = require_workspace_uuid(context)
|
||||
# Check if any models use this provider
|
||||
llm_result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.select(persistence_model.LLMModel).where(
|
||||
persistence_model.LLMModel.provider_uuid == provider_uuid
|
||||
),
|
||||
persistence_model.LLMModel,
|
||||
workspace_uuid,
|
||||
)
|
||||
persistence = self.ap.persistence_mgr
|
||||
model_types = (
|
||||
(persistence_model.LLMModel, 'LLM', 'remove_llm_model'),
|
||||
(persistence_model.EmbeddingModel, 'Embedding', 'remove_embedding_model'),
|
||||
(persistence_model.RerankModel, 'Rerank', 'remove_rerank_model'),
|
||||
)
|
||||
if llm_result.first() is not None:
|
||||
raise ValueError('Cannot delete provider: LLM models still reference it')
|
||||
|
||||
embedding_result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.select(persistence_model.EmbeddingModel).where(
|
||||
persistence_model.EmbeddingModel.provider_uuid == provider_uuid
|
||||
),
|
||||
persistence_model.EmbeddingModel,
|
||||
workspace_uuid,
|
||||
deleted_models: list[tuple[str, list[str]]] = []
|
||||
async with persistence.tenant_uow(workspace_uuid):
|
||||
# Check ownership before touching children. Lock the provider on PostgreSQL
|
||||
# so concurrent model inserts cannot race the reference check/deletion.
|
||||
provider_result = await persistence.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.select(persistence_model.ModelProvider.requester)
|
||||
.where(persistence_model.ModelProvider.uuid == provider_uuid)
|
||||
.with_for_update(),
|
||||
persistence_model.ModelProvider,
|
||||
workspace_uuid,
|
||||
)
|
||||
)
|
||||
)
|
||||
if embedding_result.first() is not None:
|
||||
raise ValueError('Cannot delete provider: Embedding models still reference it')
|
||||
provider = provider_result.first()
|
||||
if provider is None:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
if self._system_requester_is_reserved(provider.requester):
|
||||
raise ValueError('LangBot Models is managed by Cloud and cannot be modified')
|
||||
|
||||
rerank_result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.select(persistence_model.RerankModel).where(
|
||||
persistence_model.RerankModel.provider_uuid == provider_uuid
|
||||
),
|
||||
persistence_model.RerankModel,
|
||||
workspace_uuid,
|
||||
for model_type, label, remover in model_types:
|
||||
result = await persistence.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.select(model_type.uuid).where(model_type.provider_uuid == provider_uuid),
|
||||
model_type,
|
||||
workspace_uuid,
|
||||
)
|
||||
)
|
||||
model_uuids = list(result.scalars())
|
||||
if model_uuids and not cascade:
|
||||
raise ValueError(f'Cannot delete provider: {label} models still reference it')
|
||||
if model_uuids:
|
||||
# Model services have no pipeline/KB deletion side effects: they
|
||||
# delete the scoped row and evict its runtime cache. Defer eviction
|
||||
# here rather than calling those services before our commit.
|
||||
await persistence.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(model_type).where(model_type.provider_uuid == provider_uuid),
|
||||
model_type,
|
||||
workspace_uuid,
|
||||
)
|
||||
)
|
||||
deleted_models.append((remover, model_uuids))
|
||||
|
||||
# Explicit cleanup also works on legacy SQLite connections without FK
|
||||
# enforcement; never load or serialize the private credential payload.
|
||||
await persistence.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(persistence_model.CodexCredential).where(
|
||||
persistence_model.CodexCredential.provider_uuid == provider_uuid
|
||||
),
|
||||
persistence_model.CodexCredential,
|
||||
workspace_uuid,
|
||||
)
|
||||
)
|
||||
)
|
||||
if rerank_result.first() is not None:
|
||||
raise ValueError('Cannot delete provider: Rerank models still reference it')
|
||||
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(persistence_model.ModelProvider).where(
|
||||
persistence_model.ModelProvider.uuid == provider_uuid
|
||||
),
|
||||
persistence_model.ModelProvider,
|
||||
workspace_uuid,
|
||||
result = await persistence.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(persistence_model.ModelProvider).where(
|
||||
persistence_model.ModelProvider.uuid == provider_uuid
|
||||
),
|
||||
persistence_model.ModelProvider,
|
||||
workspace_uuid,
|
||||
)
|
||||
)
|
||||
)
|
||||
if getattr(result, 'rowcount', None) == 0:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
if result.rowcount == 0:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
|
||||
await self.ap.model_mgr.remove_provider(context, provider_uuid)
|
||||
async def remove_runtime() -> None:
|
||||
async with persistence.tenant_scope(workspace_uuid):
|
||||
for remover, model_uuids in deleted_models:
|
||||
for model_uuid in model_uuids:
|
||||
await getattr(self.ap.model_mgr, remover)(context, model_uuid)
|
||||
# This also closes the requester's HTTP client; models go first.
|
||||
await self.ap.model_mgr.remove_provider(context, provider_uuid)
|
||||
|
||||
if persistence.current_session() is None:
|
||||
await remove_runtime()
|
||||
else:
|
||||
# A nested UoW has not committed yet. Reuse the rollback-cancelled gate
|
||||
# and detached context boundary instead of evicting uncommitted data.
|
||||
task = create_detached_task(
|
||||
remove_runtime(),
|
||||
after_commit_manager=persistence,
|
||||
workspace_uuid=workspace_uuid,
|
||||
)
|
||||
self._deletion_tasks.add(task)
|
||||
|
||||
def completed(task: asyncio.Task[None]) -> None:
|
||||
self._deletion_tasks.discard(task)
|
||||
if not task.cancelled() and task.exception() is not None:
|
||||
self.ap.logger.error('Failed to remove deleted provider runtime', exc_info=task.exception())
|
||||
|
||||
task.add_done_callback(completed)
|
||||
|
||||
async def get_provider_model_counts(self, context: TenantContext, provider_uuid: str) -> dict:
|
||||
"""Get count of models using this provider"""
|
||||
|
||||
@@ -33,6 +33,28 @@ class ModelProvider(Base):
|
||||
)
|
||||
|
||||
|
||||
class CodexCredential(Base):
|
||||
"""Server-only OAuth state. Never joined into provider/model serialization."""
|
||||
|
||||
__tablename__ = 'codex_credentials'
|
||||
|
||||
provider_uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
|
||||
workspace_uuid = sqlalchemy.Column(sqlalchemy.String(36), nullable=False)
|
||||
payload = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default=dict)
|
||||
version = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
|
||||
lease_owner = sqlalchemy.Column(sqlalchemy.String(64), nullable=True)
|
||||
lease_until = sqlalchemy.Column(sqlalchemy.Float, nullable=False, default=0)
|
||||
__table_args__ = (
|
||||
sqlalchemy.ForeignKeyConstraint(
|
||||
['workspace_uuid', 'provider_uuid'],
|
||||
['model_providers.workspace_uuid', 'model_providers.uuid'],
|
||||
name='fk_codex_credentials_workspace_provider',
|
||||
ondelete='CASCADE',
|
||||
),
|
||||
sqlalchemy.Index('ix_codex_credentials_workspace', 'workspace_uuid'),
|
||||
)
|
||||
|
||||
|
||||
class LLMModel(Base):
|
||||
"""LLM model"""
|
||||
|
||||
|
||||
@@ -0,0 +1,48 @@
|
||||
"""Add isolated server-only Codex credentials and tenant RLS.
|
||||
|
||||
Revision ID: 0022_codex_credentials
|
||||
Revises: 0021_merge_reasoning_config
|
||||
"""
|
||||
|
||||
from alembic import op
|
||||
import sqlalchemy as sa
|
||||
|
||||
revision = '0022_codex_credentials'
|
||||
down_revision = '0021_merge_reasoning_config'
|
||||
branch_labels = None
|
||||
depends_on = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
conn = op.get_bind()
|
||||
# Fresh startup creates ORM metadata before running Alembic.
|
||||
if 'codex_credentials' not in sa.inspect(conn).get_table_names():
|
||||
op.create_table(
|
||||
'codex_credentials',
|
||||
sa.Column('provider_uuid', sa.String(255), primary_key=True),
|
||||
sa.Column('workspace_uuid', sa.String(36), nullable=False),
|
||||
sa.Column('payload', sa.JSON(), nullable=False),
|
||||
sa.Column('version', sa.Integer(), nullable=False),
|
||||
sa.Column('lease_owner', sa.String(64), nullable=True),
|
||||
sa.Column('lease_until', sa.Float(), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
['workspace_uuid', 'provider_uuid'],
|
||||
['model_providers.workspace_uuid', 'model_providers.uuid'],
|
||||
name='fk_codex_credentials_workspace_provider',
|
||||
ondelete='CASCADE',
|
||||
),
|
||||
)
|
||||
op.create_index('ix_codex_credentials_workspace', 'codex_credentials', ['workspace_uuid'])
|
||||
if conn.dialect.name == 'postgresql':
|
||||
op.execute('ALTER TABLE codex_credentials ENABLE ROW LEVEL SECURITY')
|
||||
op.execute('ALTER TABLE codex_credentials FORCE ROW LEVEL SECURITY')
|
||||
op.execute('DROP POLICY IF EXISTS langbot_workspace_isolation ON codex_credentials')
|
||||
expression = "workspace_uuid::text = NULLIF(current_setting('langbot.workspace_uuid', true), '')"
|
||||
op.execute(
|
||||
f'CREATE POLICY langbot_workspace_isolation ON codex_credentials '
|
||||
f'FOR ALL USING ({expression}) WITH CHECK ({expression})'
|
||||
)
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
op.drop_table('codex_credentials')
|
||||
@@ -62,6 +62,7 @@ _ALEMBIC_TENANT_TABLES = {
|
||||
'binary_storages',
|
||||
'mcp_servers',
|
||||
'model_providers',
|
||||
'codex_credentials',
|
||||
'llm_models',
|
||||
'embedding_models',
|
||||
'rerank_models',
|
||||
|
||||
@@ -51,6 +51,7 @@ TENANT_TABLE_COLUMNS: dict[str, str] = {
|
||||
'binary_storages': 'workspace_uuid',
|
||||
'mcp_servers': 'workspace_uuid',
|
||||
'model_providers': 'workspace_uuid',
|
||||
'codex_credentials': 'workspace_uuid',
|
||||
'llm_models': 'workspace_uuid',
|
||||
'embedding_models': 'workspace_uuid',
|
||||
'rerank_models': 'workspace_uuid',
|
||||
@@ -852,7 +853,30 @@ class TenantScopedAsyncSession(sqlalchemy_asyncio.AsyncSession):
|
||||
self._require_owner_task()
|
||||
self._enter_internal_access()
|
||||
try:
|
||||
await transaction.commit()
|
||||
# Retain the actual connection before COMMIT: after a failed SQLite
|
||||
# COMMIT the logical transaction is inactive, but the DBAPI writer
|
||||
# can still hold PENDING/RESERVED locks. Session.close()/rollback()
|
||||
# alone can then return that poisoned connection to the pool.
|
||||
connection = await super().connection()
|
||||
try:
|
||||
await transaction.commit()
|
||||
except BaseException as exc:
|
||||
cleanup = asyncio.create_task(connection.invalidate())
|
||||
# Invalidation does not access the task-owned Session. Shield
|
||||
# physical cleanup, including against repeated cancellation,
|
||||
# before the owner closes the Session and releases its scope.
|
||||
while not cleanup.done():
|
||||
try:
|
||||
await asyncio.shield(cleanup)
|
||||
except asyncio.CancelledError:
|
||||
continue
|
||||
except BaseException:
|
||||
break
|
||||
try:
|
||||
cleanup.result()
|
||||
except BaseException as cleanup_error:
|
||||
exc.add_note(f'Failed to invalidate transaction connection: {cleanup_error!r}')
|
||||
raise
|
||||
finally:
|
||||
self._exit_internal_access()
|
||||
|
||||
@@ -1369,6 +1393,7 @@ class TenantUnitOfWork:
|
||||
state.mark_rollback_only(exc_value)
|
||||
rollback_only = state.rollback_only
|
||||
committed = False
|
||||
transaction_error: BaseException | None = None
|
||||
try:
|
||||
if exc_type is None and not rollback_only:
|
||||
await typing.cast(TenantScopedAsyncSession, session)._commit_owned_transaction(
|
||||
@@ -1381,6 +1406,9 @@ class TenantUnitOfWork:
|
||||
_UOW_SESSION_CONTROL_CAPABILITY,
|
||||
transaction,
|
||||
)
|
||||
except BaseException as exc:
|
||||
transaction_error = exc
|
||||
raise
|
||||
finally:
|
||||
try:
|
||||
if self._active_transaction is not None and self._context_token is not None:
|
||||
@@ -1388,6 +1416,10 @@ class TenantUnitOfWork:
|
||||
await typing.cast(TenantScopedAsyncSession, session)._close_owned_session(
|
||||
_UOW_SESSION_CONTROL_CAPABILITY
|
||||
)
|
||||
except BaseException as cleanup_error:
|
||||
if transaction_error is None:
|
||||
raise
|
||||
transaction_error.add_note(f'Failed to close transaction Session: {cleanup_error!r}')
|
||||
finally:
|
||||
if self._database_operation_token is not None:
|
||||
_DATABASE_OPERATION_TRANSACTION.reset(self._database_operation_token)
|
||||
|
||||
@@ -0,0 +1,420 @@
|
||||
"""ChatGPT device auth with server-only credentials and cross-process refresh leases.
|
||||
|
||||
Network I/O never holds a DB transaction. A persisted CAS lease serializes refresh
|
||||
and poll; cancel fences device exchanges but waits for existing-token refreshes.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import base64
|
||||
import json
|
||||
import math
|
||||
import secrets
|
||||
import time
|
||||
from contextlib import asynccontextmanager
|
||||
from datetime import datetime, timezone
|
||||
|
||||
import httpx
|
||||
import sqlalchemy as sa
|
||||
|
||||
from ...entity.persistence.model import CodexCredential, ModelProvider
|
||||
from ...api.http.context import PrincipalType, RequestContext
|
||||
from ...api.http.authz import Permission, has_permission
|
||||
from ...api.http.service.tenant import require_workspace_uuid
|
||||
from ...workspace.errors import WorkspaceNotFoundError
|
||||
|
||||
REQUESTER = 'openai-codex'
|
||||
BASE_URL = 'https://chatgpt.com/backend-api/codex'
|
||||
ISSUER = 'https://auth.openai.com'
|
||||
CLIENT_ID = 'app_EMoamEEZ73f0CkXaXp7hrann'
|
||||
LOGIN_REQUIRED = 'ChatGPT sign-in required. Open this provider and sign in again.'
|
||||
LEASE_SECONDS = 90
|
||||
|
||||
|
||||
def validate_config(data: dict) -> None:
|
||||
if data.get('requester') != REQUESTER:
|
||||
return
|
||||
if data.get('base_url') not in (None, '', BASE_URL):
|
||||
raise ValueError('Codex uses the fixed ChatGPT endpoint; custom base URLs are not supported')
|
||||
if data.get('api_keys') not in (None, [], ''):
|
||||
raise ValueError('Codex uses ChatGPT sign-in, not API keys')
|
||||
data['base_url'] = BASE_URL
|
||||
data['api_keys'] = []
|
||||
|
||||
|
||||
def _claims(token: str) -> dict:
|
||||
"""Read routing metadata, NOT trusted LangBot identity, from issuer tokens."""
|
||||
try:
|
||||
part = token.split('.')[1]
|
||||
value = json.loads(base64.urlsafe_b64decode(part + '=' * (-len(part) % 4)))
|
||||
return value if isinstance(value, dict) else {}
|
||||
except (ValueError, IndexError, TypeError):
|
||||
return {}
|
||||
|
||||
|
||||
def _tokens(data: dict, previous: dict | None = None) -> dict:
|
||||
previous = previous or {}
|
||||
access = data.get('access_token')
|
||||
refresh = data.get('refresh_token') or previous.get('refresh_token')
|
||||
account = None
|
||||
for token in (access, data.get('id_token')):
|
||||
namespace = _claims(token or '').get('https://api.openai.com/auth', {})
|
||||
if isinstance(namespace, dict) and isinstance(namespace.get('chatgpt_account_id'), str):
|
||||
account = namespace['chatgpt_account_id']
|
||||
break
|
||||
account = account or previous.get('account_id')
|
||||
try:
|
||||
expires_at = (
|
||||
time.time() + float(data['expires_in'])
|
||||
if data.get('expires_in') is not None
|
||||
else float(_claims(access or '').get('exp', 0))
|
||||
)
|
||||
except (TypeError, ValueError):
|
||||
expires_at = 0
|
||||
if (
|
||||
not all(isinstance(v, str) and v for v in (access, refresh, account))
|
||||
or not math.isfinite(expires_at)
|
||||
or expires_at <= time.time()
|
||||
):
|
||||
raise ValueError('ChatGPT returned an incomplete authorization. Please sign in again.')
|
||||
return {
|
||||
'access_token': access,
|
||||
'refresh_token': refresh,
|
||||
'account_id': account,
|
||||
'expires_at': expires_at,
|
||||
'connection_id': previous.get('connection_id') or secrets.token_urlsafe(24),
|
||||
}
|
||||
|
||||
|
||||
class CodexAuth:
|
||||
def __init__(self, ap):
|
||||
self.ap = ap
|
||||
|
||||
def _where(self, workspace: str, provider: str):
|
||||
return (CodexCredential.workspace_uuid == workspace, CodexCredential.provider_uuid == provider)
|
||||
|
||||
async def _execute(self, statement):
|
||||
# SQLAlchemy/driver/serialization errors may embed the entire secret payload.
|
||||
try:
|
||||
return await self.ap.persistence_mgr.execute_async(statement)
|
||||
except Exception:
|
||||
raise ValueError('ChatGPT credential storage failed. Please retry.') from None
|
||||
|
||||
async def _read(self, workspace: str, provider: str) -> dict | None:
|
||||
result = await self._execute(sa.select(CodexCredential).where(*self._where(workspace, provider)))
|
||||
try:
|
||||
row = result.first()
|
||||
return dict(row._mapping) if row is not None else None
|
||||
except Exception:
|
||||
raise ValueError('ChatGPT credential storage failed. Please retry.') from None
|
||||
|
||||
async def _provider(self, context, provider: str, *, user: bool = False) -> str:
|
||||
workspace = require_workspace_uuid(context)
|
||||
if user and (
|
||||
not isinstance(context, RequestContext)
|
||||
or context.principal.principal_type != PrincipalType.ACCOUNT
|
||||
or not context.account_uuid
|
||||
or not has_permission(context, Permission.PROVIDER_SECRET_MANAGE)
|
||||
):
|
||||
raise ValueError('ChatGPT authorization requires an authorized workspace user')
|
||||
result = await self._execute(
|
||||
sa.select(ModelProvider.requester).where(
|
||||
ModelProvider.workspace_uuid == workspace, ModelProvider.uuid == provider
|
||||
)
|
||||
)
|
||||
kind = result.scalar()
|
||||
if kind is None:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
if kind != REQUESTER:
|
||||
raise ValueError('This provider does not use ChatGPT sign-in')
|
||||
return workspace
|
||||
|
||||
@asynccontextmanager
|
||||
async def _lease(self, workspace: str, provider: str, *, refresh: bool = False):
|
||||
owner = ('refresh:' if refresh else 'device:') + secrets.token_urlsafe(32)
|
||||
deadline = time.monotonic() + 65
|
||||
while True:
|
||||
now = time.time()
|
||||
result = await self._execute(
|
||||
sa.update(CodexCredential)
|
||||
.where(
|
||||
*self._where(workspace, provider),
|
||||
sa.or_(CodexCredential.lease_owner.is_(None), CodexCredential.lease_until < now),
|
||||
)
|
||||
.values(lease_owner=owner, lease_until=now + LEASE_SECONDS)
|
||||
)
|
||||
if result.rowcount == 1:
|
||||
break
|
||||
if await self._read(workspace, provider) is None:
|
||||
raise ValueError(LOGIN_REQUIRED)
|
||||
if time.monotonic() >= deadline:
|
||||
raise ValueError('ChatGPT authorization is busy. Please retry shortly.')
|
||||
await asyncio.sleep(0.1)
|
||||
try:
|
||||
yield owner
|
||||
finally:
|
||||
await self._execute(
|
||||
sa.update(CodexCredential)
|
||||
.where(*self._where(workspace, provider), CodexCredential.lease_owner == owner)
|
||||
.values(lease_owner=None, lease_until=0)
|
||||
)
|
||||
|
||||
async def _save(self, workspace: str, provider: str, owner: str, payload: dict) -> None:
|
||||
result = await self._execute(
|
||||
sa.update(CodexCredential)
|
||||
.where(
|
||||
*self._where(workspace, provider),
|
||||
CodexCredential.lease_owner == owner,
|
||||
CodexCredential.lease_until > time.time(),
|
||||
)
|
||||
.values(payload=payload, version=CodexCredential.version + 1)
|
||||
)
|
||||
if result.rowcount != 1:
|
||||
raise ValueError('ChatGPT authorization was cancelled or replaced. Please retry.')
|
||||
|
||||
async def _post(self, path: str, *, data=None, json_body=None) -> httpx.Response:
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=20, follow_redirects=False) as client:
|
||||
return await asyncio.wait_for(
|
||||
client.post(
|
||||
ISSUER + path,
|
||||
data=data,
|
||||
json=json_body,
|
||||
headers={'Accept': 'application/json', 'User-Agent': 'LangBot'},
|
||||
),
|
||||
25,
|
||||
)
|
||||
except (httpx.HTTPError, TimeoutError):
|
||||
raise ValueError('ChatGPT authorization network error. Please retry.') from None
|
||||
|
||||
@staticmethod
|
||||
def _json(response: httpx.Response) -> dict:
|
||||
try:
|
||||
value = response.json()
|
||||
if not isinstance(value, dict):
|
||||
raise ValueError
|
||||
return value
|
||||
except ValueError:
|
||||
raise ValueError('ChatGPT returned an invalid authorization response') from None
|
||||
|
||||
async def status(self, context, provider: str) -> dict:
|
||||
workspace = await self._provider(context, provider, user=True)
|
||||
row = await self._read(workspace, provider)
|
||||
payload = row['payload'] if row else {}
|
||||
tokens = payload.get('tokens')
|
||||
connected = bool(tokens and not payload.get('invalid'))
|
||||
return {
|
||||
'status': 'connected' if connected else 'expired' if payload.get('invalid') else 'disconnected',
|
||||
'connected': connected,
|
||||
'expires_at': tokens.get('expires_at') if tokens else None,
|
||||
}
|
||||
|
||||
async def start(self, context, provider: str) -> dict:
|
||||
workspace = await self._provider(context, provider, user=True)
|
||||
async with self._lease(workspace, provider) as owner:
|
||||
response = await self._post('/api/accounts/deviceauth/usercode', json_body={'client_id': CLIENT_ID})
|
||||
if response.status_code != 200:
|
||||
raise ValueError('Unable to start ChatGPT device login. Enable device code login in ChatGPT settings.')
|
||||
data = self._json(response)
|
||||
try:
|
||||
code = data.get('user_code') or data['usercode']
|
||||
device = data['device_auth_id']
|
||||
interval = max(5, min(60, int(data.get('interval') or 5)))
|
||||
if not isinstance(code, str) or not isinstance(device, str) or not code or not device:
|
||||
raise ValueError
|
||||
except (KeyError, ValueError, TypeError):
|
||||
raise ValueError('ChatGPT returned an invalid device code') from None
|
||||
now = time.time()
|
||||
try:
|
||||
expiry = data.get('expires_at')
|
||||
if expiry is None:
|
||||
expiry = now + float(data.get('expires_in', 900))
|
||||
try:
|
||||
expires_at = float(expiry)
|
||||
except ValueError:
|
||||
parsed = datetime.fromisoformat(expiry.replace('Z', '+00:00'))
|
||||
if parsed.tzinfo is None:
|
||||
parsed = parsed.replace(tzinfo=timezone.utc)
|
||||
expires_at = parsed.timestamp()
|
||||
if not math.isfinite(expires_at) or expires_at <= now:
|
||||
raise ValueError
|
||||
expires_at = min(now + 900, expires_at)
|
||||
except (ValueError, TypeError):
|
||||
raise ValueError('ChatGPT returned an invalid device code expiry') from None
|
||||
pending = {
|
||||
'authorization_id': secrets.token_urlsafe(32),
|
||||
'user_code': code,
|
||||
'device_auth_id': device,
|
||||
'account_uuid': context.account_uuid,
|
||||
'interval': interval,
|
||||
'expires_at': expires_at,
|
||||
'next_poll_at': now + interval,
|
||||
}
|
||||
row = await self._read(workspace, provider)
|
||||
payload = dict(row['payload'])
|
||||
payload['pending'] = pending
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
return {k: pending[k] for k in ('authorization_id', 'user_code', 'interval', 'expires_at')} | {
|
||||
'verification_uri': ISSUER + '/codex/device'
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _attempt(payload: dict, context, authorization_id: str) -> dict | None:
|
||||
pending = payload.get('pending')
|
||||
if not pending or pending.get('authorization_id') != authorization_id:
|
||||
return None
|
||||
if pending.get('account_uuid') != context.account_uuid:
|
||||
raise WorkspaceNotFoundError('Authorization not found')
|
||||
return pending
|
||||
|
||||
async def poll(self, context, provider: str, authorization_id: str) -> dict:
|
||||
workspace = await self._provider(context, provider, user=True)
|
||||
if not isinstance(authorization_id, str) or not authorization_id:
|
||||
raise ValueError('authorization_id is required')
|
||||
async with self._lease(workspace, provider) as owner:
|
||||
row = await self._read(workspace, provider)
|
||||
payload = dict(row['payload'])
|
||||
pending = self._attempt(payload, context, authorization_id)
|
||||
if pending is None:
|
||||
completed = payload.get('completed', {})
|
||||
if (
|
||||
completed.get('authorization_id') == authorization_id
|
||||
and completed.get('account_uuid') == context.account_uuid
|
||||
):
|
||||
return {'status': 'connected'}
|
||||
return {'status': 'expired'}
|
||||
now = time.time()
|
||||
if pending['expires_at'] <= now or pending.get('consumed'):
|
||||
payload.pop('pending', None)
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
return {'status': 'expired'}
|
||||
if pending['next_poll_at'] > now:
|
||||
return {'status': 'pending', 'interval': pending['interval']}
|
||||
pending['next_poll_at'] = now + pending['interval']
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
response = await self._post(
|
||||
'/api/accounts/deviceauth/token',
|
||||
json_body={'device_auth_id': pending['device_auth_id'], 'user_code': pending['user_code']},
|
||||
)
|
||||
if response.status_code in (403, 404, 429):
|
||||
if response.status_code == 429:
|
||||
pending['interval'] = min(60, pending['interval'] + 5)
|
||||
pending['next_poll_at'] = time.time() + pending['interval']
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
return {'status': 'pending', 'interval': pending['interval']}
|
||||
if response.status_code != 200:
|
||||
payload.pop('pending', None)
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
raise ValueError('ChatGPT device authorization failed. Please start again.')
|
||||
data = self._json(response)
|
||||
if not data.get('authorization_code') or not data.get('code_verifier'):
|
||||
payload.pop('pending', None)
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
raise ValueError('ChatGPT returned an incomplete device authorization')
|
||||
# Keep an attempt tombstone so cancel can preempt exchange, but never replay a code.
|
||||
pending['consumed'] = True
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
response = await self._post(
|
||||
'/oauth/token',
|
||||
data={
|
||||
'grant_type': 'authorization_code',
|
||||
'client_id': CLIENT_ID,
|
||||
'code': data['authorization_code'],
|
||||
'code_verifier': data['code_verifier'],
|
||||
'redirect_uri': ISSUER + '/deviceauth/callback',
|
||||
},
|
||||
)
|
||||
if response.status_code != 200:
|
||||
raise ValueError('ChatGPT token exchange failed. Please start sign-in again.')
|
||||
tokens = _tokens(self._json(response))
|
||||
await self._save(
|
||||
workspace,
|
||||
provider,
|
||||
owner,
|
||||
{
|
||||
'tokens': tokens,
|
||||
'completed': {'authorization_id': authorization_id, 'account_uuid': context.account_uuid},
|
||||
},
|
||||
)
|
||||
return {'status': 'connected'}
|
||||
|
||||
async def disconnect(self, context, provider: str) -> None:
|
||||
workspace = await self._provider(context, provider, user=True)
|
||||
await self._execute(
|
||||
sa.update(CodexCredential)
|
||||
.where(*self._where(workspace, provider))
|
||||
.values(payload={}, lease_owner=None, lease_until=0, version=CodexCredential.version + 1)
|
||||
)
|
||||
|
||||
async def cancel(self, context, provider: str, authorization_id: str) -> None:
|
||||
workspace = await self._provider(context, provider, user=True)
|
||||
deadline = time.monotonic() + 65
|
||||
while time.monotonic() < deadline:
|
||||
row = await self._read(workspace, provider)
|
||||
if row is None:
|
||||
return
|
||||
old = row['payload']
|
||||
if self._attempt(old, context, authorization_id) is None:
|
||||
return
|
||||
lease_owner = row['lease_owner']
|
||||
if lease_owner and lease_owner.startswith('refresh:') and row['lease_until'] > time.time():
|
||||
# A rotated refresh token must be committed before removing the attempt.
|
||||
await asyncio.sleep(0.1)
|
||||
continue
|
||||
payload = dict(old)
|
||||
payload.pop('pending', None)
|
||||
result = await self._execute(
|
||||
sa.update(CodexCredential)
|
||||
.where(
|
||||
*self._where(workspace, provider),
|
||||
CodexCredential.version == row['version'],
|
||||
# Lease acquisition does not change version; fence that race too.
|
||||
CodexCredential.lease_owner == lease_owner,
|
||||
)
|
||||
.values(payload=payload, lease_owner=None, lease_until=0, version=CodexCredential.version + 1)
|
||||
)
|
||||
if result.rowcount == 1:
|
||||
return
|
||||
raise ValueError('Authorization changed concurrently. Please retry cancellation.')
|
||||
|
||||
async def access(self, context, provider: str, *, rejected_token: str | None = None) -> dict:
|
||||
workspace = await self._provider(context, provider)
|
||||
row = await self._read(workspace, provider)
|
||||
payload = row['payload'] if row else {}
|
||||
tokens = payload.get('tokens')
|
||||
if not tokens or payload.get('invalid'):
|
||||
raise ValueError(LOGIN_REQUIRED)
|
||||
if tokens['expires_at'] > time.time() + 120 and tokens['access_token'] != rejected_token:
|
||||
return tokens
|
||||
async with self._lease(workspace, provider, refresh=True) as owner:
|
||||
row = await self._read(workspace, provider)
|
||||
payload = dict(row['payload'])
|
||||
tokens = payload.get('tokens')
|
||||
if not tokens or payload.get('invalid'):
|
||||
raise ValueError(LOGIN_REQUIRED)
|
||||
if tokens['expires_at'] > time.time() + 120 and tokens['access_token'] != rejected_token:
|
||||
return tokens
|
||||
response = await self._post(
|
||||
'/oauth/token',
|
||||
data={'grant_type': 'refresh_token', 'client_id': CLIENT_ID, 'refresh_token': tokens['refresh_token']},
|
||||
)
|
||||
error = self._json(response).get('error') if response.status_code in (400, 401, 403) else None
|
||||
error_code = error.get('code') if isinstance(error, dict) else error
|
||||
if error_code in (
|
||||
'invalid_grant',
|
||||
'refresh_token_reused',
|
||||
'refresh_token_expired',
|
||||
'refresh_token_revoked',
|
||||
):
|
||||
payload['invalid'] = True
|
||||
payload.pop('tokens', None)
|
||||
payload.pop('completed', None)
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
raise ValueError(LOGIN_REQUIRED)
|
||||
if response.status_code != 200:
|
||||
raise ValueError('ChatGPT token refresh temporarily failed. Please retry.')
|
||||
refreshed = _tokens(self._json(response), tokens)
|
||||
payload['tokens'] = refreshed
|
||||
await self._save(workspace, provider, owner, payload)
|
||||
return refreshed
|
||||
@@ -0,0 +1,10 @@
|
||||
"""Explicitly safe Codex failures; never construct messages from upstream bodies."""
|
||||
|
||||
|
||||
class CodexProviderError(ValueError):
|
||||
"""A known provider failure safe to expose at the HTTP boundary."""
|
||||
|
||||
def __init__(self, message: str, status_code: int = 502, error_code: str = 'codex_upstream_failure'):
|
||||
super().__init__(message)
|
||||
self.status_code = status_code
|
||||
self.error_code = error_code
|
||||
@@ -18,7 +18,7 @@ from ...discover import engine
|
||||
from ...entity.errors import provider as provider_errors
|
||||
from ...entity.persistence import model as persistence_model
|
||||
from ...workspace.entities import WorkspaceExecutionBinding
|
||||
from ...workspace.errors import WorkspaceError, WorkspaceInvariantError
|
||||
from ...workspace.errors import WorkspaceError, WorkspaceInvariantError, WorkspaceNotFoundError
|
||||
from . import requester, token
|
||||
|
||||
|
||||
@@ -638,10 +638,32 @@ class ModelManager:
|
||||
) -> requester.RuntimeLLMModel:
|
||||
execution_context = await self.resolve_execution_context(context)
|
||||
provider_info = {**model_info.get('provider', {}), 'workspace_uuid': execution_context.workspace_uuid}
|
||||
runtime_provider = await self._build_provider(
|
||||
execution_context,
|
||||
persistence_model.ModelProvider(**provider_info),
|
||||
)
|
||||
provider_uuid = model_info.get('provider_uuid') or provider_info.get('uuid')
|
||||
inline_codex = provider_info.get('requester') == 'openai-codex'
|
||||
provider_entity = persistence_model.ModelProvider(**provider_info)
|
||||
if provider_uuid:
|
||||
if provider_info.get('uuid') and provider_info['uuid'] != provider_uuid:
|
||||
raise ValueError('Conflicting provider identities')
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(persistence_model.ModelProvider).where(
|
||||
persistence_model.ModelProvider.workspace_uuid == execution_context.workspace_uuid,
|
||||
persistence_model.ModelProvider.uuid == provider_uuid,
|
||||
)
|
||||
)
|
||||
saved_provider = result.first()
|
||||
if saved_provider is None:
|
||||
if inline_codex or model_info.get('provider_uuid'):
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
else:
|
||||
saved_provider = self._coerce_provider(saved_provider, execution_context)
|
||||
if saved_provider.requester == 'openai-codex':
|
||||
# OAuth identity and transport configuration are server-owned.
|
||||
provider_entity = saved_provider
|
||||
elif inline_codex:
|
||||
raise ValueError('This provider does not use ChatGPT sign-in')
|
||||
elif inline_codex:
|
||||
raise WorkspaceNotFoundError('Provider not found')
|
||||
runtime_provider = await self._build_provider(execution_context, provider_entity)
|
||||
model_entity = persistence_model.LLMModel(
|
||||
workspace_uuid=execution_context.workspace_uuid,
|
||||
uuid=model_info.get('uuid', ''),
|
||||
@@ -723,6 +745,10 @@ class ModelManager:
|
||||
'requester_name': provider_entity.requester,
|
||||
}
|
||||
|
||||
if provider_entity.requester == 'openai-codex':
|
||||
config['provider_uuid'] = provider_entity.uuid
|
||||
config['workspace_uuid'] = context.workspace_uuid
|
||||
|
||||
if litellm_provider:
|
||||
from .requesters import litellmchat
|
||||
|
||||
|
||||
@@ -0,0 +1,423 @@
|
||||
"""Native ChatGPT Codex Responses/SSE requester (never Chat Completions)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import secrets
|
||||
import time
|
||||
from collections import OrderedDict
|
||||
|
||||
import httpx
|
||||
import langbot
|
||||
import langbot_plugin.api.entities.builtin.provider.message as pm
|
||||
|
||||
from .. import requester, reasoning
|
||||
from ..codex_auth import BASE_URL, CodexAuth, LOGIN_REQUIRED
|
||||
from ..codex_errors import CodexProviderError
|
||||
|
||||
|
||||
async def sse_events(response):
|
||||
"""Decode SSE records, including CRLF, comments, and multiline data."""
|
||||
data = []
|
||||
size = 0
|
||||
async for line in response.aiter_lines():
|
||||
if not line:
|
||||
if data:
|
||||
text = '\n'.join(data)
|
||||
if text == '[DONE]':
|
||||
return
|
||||
try:
|
||||
event = json.loads(text)
|
||||
if not isinstance(event, dict):
|
||||
raise ValueError
|
||||
except ValueError:
|
||||
raise ValueError('Codex returned an invalid stream event') from None
|
||||
yield event
|
||||
data, size = [], 0
|
||||
elif line.startswith('data:'):
|
||||
value = line[5:]
|
||||
if value.startswith(' '):
|
||||
value = value[1:]
|
||||
size += len(value)
|
||||
if size > 4 * 1024 * 1024:
|
||||
raise ValueError('Codex stream event exceeds the size limit')
|
||||
data.append(value)
|
||||
# SSE requires the blank separator; unterminated records cannot prove completion.
|
||||
|
||||
|
||||
def _content(message):
|
||||
content = message.content
|
||||
if isinstance(content, str):
|
||||
return [{'type': 'output_text' if message.role == 'assistant' else 'input_text', 'text': content}]
|
||||
result = []
|
||||
for part in content or []:
|
||||
if part.type == 'text':
|
||||
result.append(
|
||||
{'type': 'output_text' if message.role == 'assistant' else 'input_text', 'text': part.text or ''}
|
||||
)
|
||||
elif part.type == 'image_url' and part.image_url is not None:
|
||||
result.append({'type': 'input_image', 'image_url': part.image_url.url})
|
||||
elif part.type == 'image_base64' and part.image_base64:
|
||||
value = part.image_base64
|
||||
result.append(
|
||||
{
|
||||
'type': 'input_image',
|
||||
'image_url': value if value.startswith('data:') else 'data:image/png;base64,' + value,
|
||||
}
|
||||
)
|
||||
else:
|
||||
raise ValueError('Codex supports text and images only; this message contains unsupported content')
|
||||
return result
|
||||
|
||||
|
||||
def _tool(item):
|
||||
try:
|
||||
return pm.ToolCall(
|
||||
id=item['call_id'],
|
||||
type='function',
|
||||
function=pm.FunctionCall(name=item['name'], arguments=item.get('arguments') or ''),
|
||||
)
|
||||
except (KeyError, ValueError, TypeError):
|
||||
raise ValueError('Codex returned an invalid function call') from None
|
||||
|
||||
|
||||
def _usage(response):
|
||||
usage = response.get('usage') or {}
|
||||
return {
|
||||
'prompt_tokens': usage.get('input_tokens', 0),
|
||||
'completion_tokens': usage.get('output_tokens', 0),
|
||||
'total_tokens': usage.get('total_tokens', usage.get('input_tokens', 0) + usage.get('output_tokens', 0)),
|
||||
'prompt_tokens_details': usage.get('input_tokens_details', {}),
|
||||
'completion_tokens_details': usage.get('output_tokens_details', {}),
|
||||
}
|
||||
|
||||
|
||||
class CodexRequester(requester.ProviderAPIRequester):
|
||||
async def initialize(self):
|
||||
self.auth = CodexAuth(self.ap)
|
||||
self.workspace = self.requester_cfg['workspace_uuid']
|
||||
self.provider = self.requester_cfg['provider_uuid']
|
||||
# Opaque replay data stays server-side; handles are scoped to the same query,
|
||||
# model and OAuth connection. No token or encrypted reasoning enters messages.
|
||||
self._replay = OrderedDict()
|
||||
|
||||
async def aclose(self):
|
||||
self._replay.clear()
|
||||
|
||||
def get_reasoning_capabilities(self, model):
|
||||
return {
|
||||
'supported': True,
|
||||
'levels': ['provider_default', 'low', 'medium', 'high', 'xhigh'],
|
||||
'source': 'provider',
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _headers(tokens, *, stream=False):
|
||||
return {
|
||||
'Authorization': 'Bearer ' + tokens['access_token'],
|
||||
'ChatGPT-Account-ID': tokens['account_id'],
|
||||
'User-Agent': 'LangBot/' + langbot.__version__,
|
||||
'originator': 'langbot',
|
||||
'OpenAI-Beta': 'responses=experimental',
|
||||
'Accept': 'text/event-stream' if stream else 'application/json',
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _http_error(status):
|
||||
if status == 401:
|
||||
# Upstream authentication is not LangBot authentication: HTTP401 would
|
||||
# make the browser discard its own valid user session.
|
||||
return CodexProviderError(LOGIN_REQUIRED, 400, 'codex_reauthentication_required')
|
||||
if status == 429:
|
||||
return CodexProviderError(
|
||||
'ChatGPT request was limited (rate limit or usage restriction). Please retry later or check your plan.',
|
||||
429,
|
||||
'codex_rate_limited',
|
||||
)
|
||||
if status == 403:
|
||||
return CodexProviderError(
|
||||
'ChatGPT denied this request. Check subscription and workspace permissions.',
|
||||
403,
|
||||
'codex_access_denied',
|
||||
)
|
||||
if status == 400:
|
||||
return CodexProviderError(
|
||||
'ChatGPT rejected the model or request. Check the selected model and request settings.',
|
||||
400,
|
||||
'codex_invalid_request',
|
||||
)
|
||||
return CodexProviderError('ChatGPT Codex upstream request failed. Please retry later.')
|
||||
|
||||
async def _response_error(self, response):
|
||||
# Inspect only a bounded 429 error record and an allowlisted machine code.
|
||||
# Never expose upstream prose, reset metadata, headers or credentials.
|
||||
if response.status_code == 429:
|
||||
payload = bytearray()
|
||||
async for chunk in response.aiter_bytes():
|
||||
if len(payload) + len(chunk) > 8192:
|
||||
return self._http_error(429)
|
||||
payload.extend(chunk)
|
||||
try:
|
||||
data = json.loads(payload)
|
||||
error = data.get('error') if isinstance(data, dict) else None
|
||||
if isinstance(error, dict) and (
|
||||
error.get('type') == 'usage_limit_reached' or error.get('code') == 'usage_limit_reached'
|
||||
):
|
||||
return CodexProviderError(
|
||||
'ChatGPT subscription usage limit reached. Please retry later or check your plan.',
|
||||
429,
|
||||
'codex_usage_limit_reached',
|
||||
)
|
||||
except (ValueError, UnicodeError):
|
||||
pass
|
||||
return self._http_error(response.status_code)
|
||||
|
||||
def _scope(self, query, model, tokens):
|
||||
return (
|
||||
id(query),
|
||||
getattr(query, 'query_id', None),
|
||||
model.model_entity.name,
|
||||
tokens.get('connection_id'),
|
||||
tokens['account_id'],
|
||||
)
|
||||
|
||||
def _body(self, query, model, messages, funcs, extra_args, tokens):
|
||||
args = {**(model.model_entity.extra_args or {}), **(extra_args or {})}
|
||||
# Never permit credentials, transport overrides, store/history or arbitrary
|
||||
# SDK kwargs to be smuggled through model advanced parameters.
|
||||
allowed = {'reasoning', 'text', 'parallel_tool_calls', 'tool_choice'}
|
||||
unknown = set(args) - allowed
|
||||
if unknown:
|
||||
raise ValueError('Unsupported Codex advanced parameters: ' + ', '.join(sorted(unknown)))
|
||||
instructions = []
|
||||
items = []
|
||||
scope = self._scope(query, model, tokens)
|
||||
for message in messages:
|
||||
if message.role in ('system', 'developer'):
|
||||
instructions.append('\n'.join(p['text'] for p in _content(message) if 'text' in p))
|
||||
continue
|
||||
if message.role == 'tool':
|
||||
if not message.tool_call_id:
|
||||
raise ValueError('Codex tool results require a tool_call_id')
|
||||
output = (
|
||||
message.content
|
||||
if isinstance(message.content, str)
|
||||
else json.dumps([p.model_dump(exclude_none=True) for p in message.content or []])
|
||||
)
|
||||
items.append({'type': 'function_call_output', 'call_id': message.tool_call_id, 'output': output or ''})
|
||||
continue
|
||||
if message.role not in ('assistant', 'user'):
|
||||
raise ValueError('Unsupported Codex message role')
|
||||
handle = (message.provider_specific_fields or {}).get('codex_replay_id')
|
||||
cached = self._replay.get(handle) if isinstance(handle, str) else None
|
||||
if query is not None and cached and cached[0] == scope and cached[1] > time.time():
|
||||
items.extend(cached[2])
|
||||
continue
|
||||
content = _content(message)
|
||||
if content:
|
||||
items.append({'type': 'message', 'role': message.role, 'content': content})
|
||||
for call in message.tool_calls or []:
|
||||
items.append(
|
||||
{
|
||||
'type': 'function_call',
|
||||
'call_id': call.id,
|
||||
'name': call.function.name,
|
||||
'arguments': call.function.arguments,
|
||||
}
|
||||
)
|
||||
body = {
|
||||
**args,
|
||||
'model': model.model_entity.name,
|
||||
'instructions': '\n\n'.join(instructions),
|
||||
'input': items,
|
||||
'store': False,
|
||||
'stream': True,
|
||||
'include': ['reasoning.encrypted_content'],
|
||||
}
|
||||
level = reasoning.normalize_reasoning_config(getattr(model.model_entity, 'reasoning_config', None))['level']
|
||||
if level != 'provider_default':
|
||||
reasoning.validate_reasoning_capabilities(
|
||||
{'level': level}, self.get_reasoning_capabilities(model), model.model_entity.name
|
||||
)
|
||||
body['reasoning'] = {'effort': level, 'summary': 'auto'}
|
||||
if funcs:
|
||||
body['tools'] = [
|
||||
{
|
||||
'type': 'function',
|
||||
'name': f.name,
|
||||
'description': f.description,
|
||||
'parameters': f.parameters,
|
||||
'strict': False,
|
||||
}
|
||||
for f in funcs
|
||||
]
|
||||
return body
|
||||
|
||||
async def _events(self, query, model, messages, funcs, extra_args):
|
||||
tokens = await self.auth.access(self.workspace, self.provider)
|
||||
try:
|
||||
async with asyncio.timeout(300), httpx.AsyncClient(timeout=120, follow_redirects=False) as client:
|
||||
for attempt in range(2):
|
||||
body = self._body(query, model, messages, funcs, extra_args, tokens)
|
||||
async with client.stream(
|
||||
'POST', BASE_URL + '/responses', json=body, headers=self._headers(tokens, stream=True)
|
||||
) as response:
|
||||
if response.status_code == 401 and attempt == 0:
|
||||
tokens = await self.auth.access(
|
||||
self.workspace, self.provider, rejected_token=tokens['access_token']
|
||||
)
|
||||
continue
|
||||
if response.status_code != 200:
|
||||
raise await self._response_error(response)
|
||||
async for event in sse_events(response):
|
||||
yield event, tokens
|
||||
return
|
||||
except (httpx.HTTPError, TimeoutError):
|
||||
raise ValueError('ChatGPT Codex network error or timeout. Please retry.') from None
|
||||
|
||||
async def _chunks(self, query, model, messages, funcs, extra_args, remove_think, usage_out):
|
||||
text = ''
|
||||
seen_calls = set()
|
||||
output_items = {}
|
||||
response_id = None
|
||||
async for event, tokens in self._events(query, model, messages, funcs, extra_args):
|
||||
kind = event.get('type')
|
||||
response = event.get('response') or {}
|
||||
response_id = response.get('id') or response_id
|
||||
if kind in ('error', 'response.failed', 'response.incomplete'):
|
||||
raise CodexProviderError('ChatGPT Codex response failed or was incomplete. Please retry.')
|
||||
if kind == 'response.output_text.delta':
|
||||
delta = event.get('delta', '')
|
||||
text += delta
|
||||
yield pm.MessageChunk(role='assistant', content=delta, resp_message_id=response_id)
|
||||
elif kind in ('response.reasoning_summary_text.delta', 'response.reasoning_text.delta'):
|
||||
if not remove_think:
|
||||
yield pm.MessageChunk(
|
||||
role='assistant',
|
||||
content='',
|
||||
provider_specific_fields={'reasoning_content': event.get('delta', '')},
|
||||
)
|
||||
elif kind == 'response.output_item.done':
|
||||
item = event.get('item') or {}
|
||||
output_items[event.get('output_index', len(output_items))] = item
|
||||
if item.get('type') == 'function_call' and item.get('call_id') not in seen_calls:
|
||||
seen_calls.add(item.get('call_id'))
|
||||
yield pm.MessageChunk(role='assistant', content='', tool_calls=[_tool(item)])
|
||||
elif kind in ('response.completed', 'response.done'):
|
||||
if response.get('status') not in (None, 'completed'):
|
||||
raise CodexProviderError('ChatGPT Codex response was not completed')
|
||||
output = response.get('output') or [output_items[k] for k in sorted(output_items)]
|
||||
for item in output:
|
||||
if item.get('type') == 'function_call' and item.get('call_id') not in seen_calls:
|
||||
seen_calls.add(item.get('call_id'))
|
||||
yield pm.MessageChunk(role='assistant', content='', tool_calls=[_tool(item)])
|
||||
# Some servers send only the terminal output, without text deltas.
|
||||
final_text = ''.join(
|
||||
p.get('text', '')
|
||||
for item in output
|
||||
if item.get('type') == 'message'
|
||||
for p in item.get('content', [])
|
||||
if p.get('type') == 'output_text'
|
||||
)
|
||||
if not text and final_text:
|
||||
text = final_text
|
||||
yield pm.MessageChunk(role='assistant', content=text, resp_message_id=response_id)
|
||||
usage_out.update(_usage(response))
|
||||
if query is not None:
|
||||
if query.variables is None:
|
||||
query.variables = {}
|
||||
query.variables[requester.STREAM_USAGE_QUERY_VARIABLE] = dict(usage_out)
|
||||
fields = None
|
||||
if query is not None and output:
|
||||
handle = secrets.token_urlsafe(24)
|
||||
self._replay[handle] = (self._scope(query, model, tokens), time.time() + 3600, output)
|
||||
while len(self._replay) > 64:
|
||||
self._replay.popitem(last=False)
|
||||
fields = {'codex_replay_id': handle}
|
||||
yield pm.MessageChunk(
|
||||
role='assistant',
|
||||
content='',
|
||||
all_content=text,
|
||||
is_final=True,
|
||||
resp_message_id=response_id,
|
||||
provider_specific_fields=fields,
|
||||
)
|
||||
return
|
||||
raise CodexProviderError('ChatGPT Codex stream ended before completion. Please retry.')
|
||||
|
||||
async def invoke_llm_stream(self, query, model, messages, funcs=None, extra_args=None, remove_think=False):
|
||||
async for chunk in self._chunks(query, model, messages, funcs, extra_args, remove_think, {}):
|
||||
yield chunk
|
||||
|
||||
async def invoke_llm(self, query, model, messages, funcs=None, extra_args=None, remove_think=False):
|
||||
usage = {}
|
||||
text = ''
|
||||
calls = []
|
||||
fields = {}
|
||||
response_id = None
|
||||
async for chunk in self._chunks(query, model, messages, funcs, extra_args, remove_think, usage):
|
||||
text += chunk.content or ''
|
||||
calls.extend(chunk.tool_calls or [])
|
||||
response_id = chunk.resp_message_id or response_id
|
||||
for key, value in (chunk.provider_specific_fields or {}).items():
|
||||
fields[key] = fields.get(key, '') + value if key == 'reasoning_content' else value
|
||||
return pm.Message(
|
||||
role='assistant',
|
||||
content=text,
|
||||
tool_calls=calls or None,
|
||||
resp_message_id=response_id,
|
||||
provider_specific_fields=fields or None,
|
||||
), usage
|
||||
|
||||
async def scan_models(self, api_key=None):
|
||||
tokens = await self.auth.access(self.workspace, self.provider)
|
||||
try:
|
||||
async with asyncio.timeout(90), httpx.AsyncClient(timeout=30, follow_redirects=False) as client:
|
||||
for attempt in range(2):
|
||||
response = await client.get(
|
||||
BASE_URL + '/models',
|
||||
params={'client_version': langbot.__version__},
|
||||
headers=self._headers(tokens),
|
||||
)
|
||||
if response.status_code == 401 and attempt == 0:
|
||||
tokens = await self.auth.access(
|
||||
self.workspace, self.provider, rejected_token=tokens['access_token']
|
||||
)
|
||||
continue
|
||||
if response.status_code != 200:
|
||||
raise await self._response_error(response)
|
||||
data = response.json()
|
||||
if not isinstance(data, dict) or not isinstance(data.get('models'), list):
|
||||
raise ValueError('ChatGPT returned an invalid model catalog')
|
||||
result = {}
|
||||
for item in data['models']:
|
||||
name = item.get('slug') or item.get('id')
|
||||
if not isinstance(name, str) or not name or item.get('visibility') == 'hide':
|
||||
continue
|
||||
modalities = item.get('input_modalities') or ['text']
|
||||
abilities = ['func_call']
|
||||
if 'image' in modalities:
|
||||
abilities.append('vision')
|
||||
if item.get('supported_reasoning_levels'):
|
||||
abilities.append('reasoning')
|
||||
result[name] = {
|
||||
'id': name,
|
||||
'name': name,
|
||||
'type': 'llm',
|
||||
'abilities': abilities,
|
||||
'display_name': item.get('display_name'),
|
||||
'description': item.get('description'),
|
||||
'context_length': item.get('context_window'),
|
||||
'input_modalities': modalities,
|
||||
'output_modalities': ['text'],
|
||||
'owned_by': 'openai',
|
||||
}
|
||||
return {'models': list(result.values()), 'debug': None}
|
||||
except (httpx.HTTPError, TimeoutError):
|
||||
raise ValueError('ChatGPT model discovery network error. Please retry.') from None
|
||||
except (ValueError, TypeError, KeyError, AttributeError) as exc:
|
||||
# Never echo upstream response bodies (which may contain credentials).
|
||||
if isinstance(exc, ValueError) and str(exc).startswith(('ChatGPT', 'Codex')):
|
||||
raise
|
||||
raise ValueError('ChatGPT returned an invalid model catalog') from None
|
||||
@@ -0,0 +1,27 @@
|
||||
apiVersion: v1
|
||||
kind: LLMAPIRequester
|
||||
metadata:
|
||||
name: openai-codex
|
||||
label:
|
||||
en_US: OpenAI Codex
|
||||
zh_Hans: OpenAI Codex
|
||||
ja_JP: OpenAI Codex
|
||||
icon: openai.svg
|
||||
spec:
|
||||
config:
|
||||
- name: base_url
|
||||
label:
|
||||
en_US: ChatGPT endpoint
|
||||
zh_Hans: ChatGPT 服务地址
|
||||
ja_JP: ChatGPT エンドポイント
|
||||
type: string
|
||||
required: false
|
||||
default: https://chatgpt.com/backend-api/codex
|
||||
alias: "openai codex ChatGPT subscription OAuth 订阅"
|
||||
support_type:
|
||||
- llm
|
||||
provider_category: manufacturer
|
||||
execution:
|
||||
python:
|
||||
path: ./codex.py
|
||||
attr: CodexRequester
|
||||
Reference in New Issue
Block a user