chore: merge master into dev/4.11.x

src/langbot/pkg/persistence/alembic/versions/0018_add_llm_reasoning_config.py

@@ -0,0 +1,57 @@
+"""add llm reasoning config
+
+Revision ID: 0018_llm_reasoning_config
+Revises: 0017_oss_workspace_identity
+Create Date: 2026-07-27
+"""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '0018_llm_reasoning_config'
+down_revision = '0017_oss_workspace_identity'
+branch_labels = None
+depends_on = None
+
+
+_LLM_MODELS = sa.table(
+    'llm_models',
+    sa.column('reasoning_config', sa.JSON()),
+)
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    if 'llm_models' not in inspector.get_table_names():
+        return
+
+    columns = {column['name'] for column in inspector.get_columns('llm_models')}
+    if 'reasoning_config' in columns:
+        return
+
+    op.add_column(
+        'llm_models',
+        sa.Column(
+            'reasoning_config',
+            sa.JSON(),
+            nullable=True,
+            server_default=sa.text('\'{"level":"provider_default"}\''),
+        ),
+    )
+    conn.execute(_LLM_MODELS.update().values(reasoning_config={'level': 'provider_default'}))
+    with op.batch_alter_table('llm_models') as batch_op:
+        batch_op.alter_column('reasoning_config', existing_type=sa.JSON(), nullable=False)
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    if 'llm_models' not in inspector.get_table_names():
+        return
+    columns = {column['name'] for column in inspector.get_columns('llm_models')}
+    if 'reasoning_config' in columns:
+        with op.batch_alter_table('llm_models') as batch_op:
+            batch_op.drop_column('reasoning_config')

src/langbot/pkg/persistence/alembic/versions/001a_pgvector_dimension_3072.py

@@ -0,0 +1,43 @@
+"""enable 3072-dimensional pgvector embeddings
+
+Revision ID: 001a_pgvector_dimension_3072
+Revises: 0019_single_workspace_owner
+Create Date: 2026-08-05
+"""
+
+from __future__ import annotations
+import sqlalchemy as sa
+from alembic import op
+
+revision = '001a_pgvector_dimension_3072'
+down_revision = '0019_single_workspace_owner'
+branch_labels = None
+depends_on = None
+_TABLE = 'langbot_vectors'
+_CHECK = 'ck_langbot_vectors_embedding_dimension_enabled'
+_INDEX = 'ix_langbot_vectors_hnsw_cosine_3072'
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    if conn.dialect.name != 'postgresql' or _TABLE not in sa.inspect(conn).get_table_names():
+        return
+    op.drop_constraint(_CHECK, _TABLE, type_='check')
+    op.create_check_constraint(_CHECK, _TABLE, 'embedding_dimension IN (384, 512, 768, 1024, 1536, 3072)')
+    op.execute(
+        sa.text(
+            f'CREATE INDEX {_INDEX} ON {_TABLE} USING hnsw ((embedding::halfvec(3072)) halfvec_cosine_ops) WHERE embedding_dimension = 3072'
+        )
+    )
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+    if conn.dialect.name != 'postgresql' or _TABLE not in sa.inspect(conn).get_table_names():
+        return
+    count = conn.scalar(sa.text(f'SELECT COUNT(*) FROM {_TABLE} WHERE embedding_dimension = 3072'))
+    if count:
+        raise RuntimeError('Cannot disable 3072-dimensional pgvector while matching embeddings exist')
+    op.drop_index(_INDEX, table_name=_TABLE)
+    op.drop_constraint(_CHECK, _TABLE, type_='check')
+    op.create_check_constraint(_CHECK, _TABLE, 'embedding_dimension IN (384, 512, 768, 1024, 1536)')

src/langbot/pkg/persistence/alembic/versions/0020_workspace_membership_source.py

@@ -0,0 +1,49 @@
+"""add explicit Workspace membership source
+
+Revision ID: 0020_membership_source
+Revises: 001a_pgvector_dimension_3072
+Create Date: 2026-08-06
+"""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '0020_membership_source'
+down_revision = '001a_pgvector_dimension_3072'
+branch_labels = None
+depends_on = None
+
+_CONSTRAINT_NAME = 'ck_workspace_memberships_source'
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    if 'workspace_memberships' not in inspector.get_table_names():
+        return
+    if 'source' in {column['name'] for column in inspector.get_columns('workspace_memberships')}:
+        return
+
+    # No durable historical field distinguishes Directory-created revision-zero
+    # rows from Core invitations. Protect every existing row; production can
+    # reclassify separately after UUIDs have been verified against Space.
+    with op.batch_alter_table('workspace_memberships') as batch_op:
+        batch_op.add_column(sa.Column('source', sa.String(length=32), nullable=False, server_default='local'))
+        batch_op.create_check_constraint(
+            _CONSTRAINT_NAME,
+            "source IN ('local', 'cloud_projection')",
+        )
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    if 'workspace_memberships' not in inspector.get_table_names():
+        return
+    if 'source' not in {column['name'] for column in inspector.get_columns('workspace_memberships')}:
+        return
+    with op.batch_alter_table('workspace_memberships') as batch_op:
+        batch_op.drop_constraint(_CONSTRAINT_NAME, type_='check')
+        batch_op.drop_column('source')

src/langbot/pkg/persistence/alembic/versions/0021_merge_reasoning_config.py

@@ -0,0 +1,21 @@
+"""merge reasoning config with the main migration branch
+
+Revision ID: 0021_merge_reasoning_config
+Revises: 0020_membership_source, 0018_llm_reasoning_config
+Create Date: 2026-08-09
+"""
+
+from __future__ import annotations
+
+revision = '0021_merge_reasoning_config'
+down_revision = ('0020_membership_source', '0018_llm_reasoning_config')
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    pass
+
+
+def downgrade() -> None:
+    pass

src/langbot/pkg/persistence/alembic/versions/0022_merge_agent_reasoning_heads.py

@@ -0,0 +1,21 @@
+"""merge AgentRunner and model reasoning migration heads
+
+Revision ID: 0022_merge_agent_reasoning_heads
+Revises: 0020_merge_agent_cloud_heads, 0021_merge_reasoning_config
+Create Date: 2026-08-14
+"""
+
+from __future__ import annotations
+
+revision = '0022_merge_agent_reasoning_heads'
+down_revision = ('0020_merge_agent_cloud_heads', '0021_merge_reasoning_config')
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    pass
+
+
+def downgrade() -> None:
+    pass

src/langbot/pkg/persistence/mgr.py

@@ -98,7 +98,7 @@ _WORKSPACE_ALEMBIC_REVISION = '0009_workspace_tenancy'
 _RESOURCE_SCOPE_ALEMBIC_REVISION = '0010_scope_resources'
 _OSS_WORKSPACE_METADATA_KEY = 'oss_workspace_uuid'
 _RELEASE_MIGRATION_ADVISORY_LOCK_ID = 0x4C414E47424F5432
-_PGVECTOR_ALLOWED_DIMENSIONS = (384, 512, 768, 1024, 1536)
+_PGVECTOR_ALLOWED_DIMENSIONS = (384, 512, 768, 1024, 1536, 3072)
 _RUNTIME_SCHEMA = 'public'
 _ALEMBIC_RUNTIME_TABLE = 'alembic_version'
 _RUNTIME_TABLE_PRIVILEGES = frozenset({'SELECT', 'INSERT', 'UPDATE', 'DELETE'})
@@ -1311,14 +1311,16 @@ class PersistenceManager:
             index = by_index.get(index_name)
             index_definition = normalized(None if index is None else index['definition'])
             predicate = normalized(None if index is None else index['predicate'])
+            vector_type = 'halfvec' if dimension > 2000 else 'vector'
+            operator_class = f'{vector_type}_cosine_ops'
             if (
                 index is None
                 or index['access_method'] != 'hnsw'
                 or index['is_valid'] is not True
                 or index['is_ready'] is not True
-                or f'vector({dimension})' not in index_definition
-                or f'(embedding)::vector({dimension})' not in index_definition
-                or 'vector_cosine_ops' not in index_definition
+                or f'{vector_type}({dimension})' not in index_definition
+                or f'(embedding)::{vector_type}({dimension})' not in index_definition
+                or operator_class not in index_definition
                 or predicate.strip('() ') != f'embedding_dimension = {dimension}'
             ):
                 raise RuntimeError(f'PostgreSQL pgvector ANN index {index_name!r} is invalid')

src/langbot/pkg/persistence/tenant_uow.py

@@ -13,7 +13,7 @@ import typing
 import sqlalchemy
 import sqlalchemy.ext.asyncio as sqlalchemy_asyncio
 import sqlalchemy.orm as sqlalchemy_orm
-from pgvector.sqlalchemy import Vector
+from pgvector.sqlalchemy import HALFVEC, Vector
 from sqlalchemy.dialects.postgresql.dml import OnConflictDoNothing as PostgreSQLOnConflictDoNothing
 from sqlalchemy.dialects.postgresql.dml import OnConflictDoUpdate as PostgreSQLOnConflictDoUpdate
 from sqlalchemy.dialects.sqlite.dml import OnConflictDoNothing as SQLiteOnConflictDoNothing
@@ -282,7 +282,7 @@ def _validate_scoped_sql_type(
         return
     seen.add(identity)
 
-    if type(sql_type) is Vector:
+    if type(sql_type) in {Vector, HALFVEC}:
         return
     if not type(sql_type).__module__.startswith('sqlalchemy.'):
         raise ScopedSessionTransactionError('TenantUnitOfWork does not allow custom SQL types in public statements')
@@ -463,7 +463,7 @@ def _validate_scoped_statement_call(args: tuple[typing.Any, ...], kwargs: dict[s
         if isinstance(element, sqlalchemy.sql.elements.BindParameter) and element.literal_execute:
             raise ScopedSessionTransactionError('TenantUnitOfWork does not allow literal-execute SQL parameters')
 
-        if isinstance(element, sqlalchemy.sql.elements.Cast) and type(element.type) is not Vector:
+        if isinstance(element, sqlalchemy.sql.elements.Cast) and type(element.type) not in {Vector, HALFVEC}:
             raise ScopedSessionTransactionError(
                 'TenantUnitOfWork only allows the trusted pgvector cast used by tenant vector search'
             )