[feat] Unify eval loops

.gitignore

@@ -11,6 +11,7 @@
 **/*.pem
 **/*dont_commit_me*
 web/packages/agenta-api-client/dist/
+web/tsconfig.tsbuildinfo
 
 __pycache__/
 **/__pycache__/

AGENTS.md

@@ -176,6 +176,26 @@ Concrete examples:
 - Legacy app storage marker (`WORKFLOW_MARKER_KEY`): `api/oss/src/core/applications/service.py`
 - Legacy dedup key normalization (`__dedup_id__` <-> `testcase_dedup_id`): `api/oss/src/apis/fastapi/testsets/router.py`
 
+### Alembic migration chains (OSS + EE)
+
+Migrations live in two separate, parallel chains that must each resolve to a
+single head:
+- OSS: `api/oss/databases/postgres/migrations/core/versions/`
+- EE: `api/ee/databases/postgres/migrations/core/versions/`
+
+Rules:
+- After adding/editing/renaming any migration, verify each chain has exactly ONE
+  head with the bundled tool: from each `.../migrations/` directory run
+  `python3 find_head.py core` and confirm the `Heads:` list has a single entry.
+  Run it for BOTH OSS and EE.
+- New migrations chain linearly after the existing head — never fork off an older
+  node (a fork produces two heads; alembic then can't resolve a linear upgrade).
+- Revision ids must be globally unique within a chain. A duplicate id makes
+  alembic silently skip one file (the migration never runs).
+- The EE chain and the OSS chain are parallel, so an OSS migration chains after
+  the OSS head while its EE counterpart chains after the EE head — same revision id,
+  possibly different `down_revision`.
+
 ### Router and function style conventions
 
 Router style:

api/ee/databases/postgres/migrations/core/data_migrations/applications_workflow.py

@@ -254,9 +254,11 @@ def check_url_safety(cls, v: Any) -> Any:  # noqa: N805
             return v
 
     from oss.src.dbs.postgres.git.mappings import map_dto_to_dbe
-    from oss.src.dbs.postgres.shared.engine import engine as db_engine
+    from oss.src.dbs.postgres.shared.engine import get_transactions_engine
     from datetime import datetime, timezone
 
+    db_engine = get_transactions_engine()
+
     workflow_create = WorkflowCreate(
         **application_create.model_dump(mode="json"),
     )
@@ -267,7 +269,7 @@ def check_url_safety(cls, v: Any) -> Any:  # noqa: N805
 
     # Avoid slug collision with existing workflow artifacts (e.g. evaluators)
     artifact_slug = git_artifact_create.slug
-    async with db_engine.core_session() as session:
+    async with db_engine.session() as session:
         existing = (
             await session.execute(
                 select(WorkflowArtifactDBE).filter(
@@ -298,7 +300,7 @@ def check_url_safety(cls, v: Any) -> Any:  # noqa: N805
         dto=artifact_dto,
     )
 
-    async with db_engine.core_session() as session:
+    async with db_engine.session() as session:
         session.add(artifact_dbe)
         await session.commit()
 
@@ -364,7 +366,7 @@ def check_url_safety(cls, v: Any) -> Any:  # noqa: N805
             dto=variant_dto,
         )
 
-        async with db_engine.core_session() as session:
+        async with db_engine.session() as session:
             session.add(variant_dbe)
             await session.commit()
 
@@ -415,7 +417,7 @@ def check_url_safety(cls, v: Any) -> Any:  # noqa: N805
                 dto=revision_dto,
             )
 
-            async with db_engine.core_session() as session:
+            async with db_engine.session() as session:
                 session.add(revision_dbe)
                 await session.commit()
 

api/ee/databases/postgres/migrations/core/env.py

@@ -6,7 +6,7 @@
 
 from alembic import context
 
-from oss.src.dbs.postgres.shared.engine import engine
+from oss.src.utils.env import env
 from oss.src.dbs.postgres.shared.base import Base
 
 # Side-effect imports: register SQLAlchemy models with Base.metadata
@@ -29,7 +29,7 @@
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
 config = context.config
-config.set_main_option("sqlalchemy.url", engine.postgres_uri_core)  # type: ignore
+config.set_main_option("sqlalchemy.url", env.postgres.uri_core)
 
 
 # Interpret the config file for Python logging.

api/ee/databases/postgres/migrations/core/versions/a1d2e3f4a5b6_add_default_evaluation_queues.py

@@ -0,0 +1,41 @@
+"""add default evaluation queues
+
+Revision ID: a1d2e3f4a5b6
+Revises: e6f7a8b9c0d2
+Create Date: 2026-05-15 00:00:00
+
+Previously shared revision id `a1b2c3d4e5f6` with
+`drop_corrupted_metrics_for_some_runs`, so alembic skipped it and the index
+below never ran. Renamed to `a1d2e3f4a5b6`. The EE chain extends past the shared
+OSS head `e6f7a8b9c0d1` with EE-only migrations
+(`9d3e8f0a1b2c -> a1b2c3d4e5f7 -> b2c3d4e5f7a8`), so this EE copy chains after
+`b2c3d4e5f7a8` while the OSS copy chains after `e6f7a8b9c0d1`.
+
+The partial unique index covers ALL default queues (active or archived), so
+there is at most ONE default queue row per (project_id, run_id) for the lifetime
+of the run. Archiving a default does NOT free the slot — the single row is
+archived/unarchived in place by reconcile, and user-facing archive of a default
+is forbidden in the service layer.
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+
+revision: str = "a1d2e3f4a5b6"
+down_revision: Union[str, None] = "e6f7a8b9c0d2"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.execute("DROP INDEX IF EXISTS ux_evaluation_queues_default_per_run")
+    op.execute("""
+        CREATE UNIQUE INDEX ux_evaluation_queues_default_per_run
+        ON evaluation_queues (project_id, run_id)
+        WHERE (flags ->> 'is_default')::boolean = true
+    """)
+
+
+def downgrade() -> None:
+    op.execute("DROP INDEX IF EXISTS ux_evaluation_queues_default_per_run")