feat(run): Propagates model_name from the gateway request through the runtime and persistence stack to the SQLite database. (#2775)

* feat(run): propagate model_name from gateway request context to persistence layer

Pass model_name through the full run creation pipeline — from
RunCreateRequest.context in the gateway, through RunManager, to the
RunStore interface and SQL persistence. This enables client-specified
model selection to be recorded per-run in the database.

* feat(run): add model allowlist validation and effective model name capture

- Validate model_name against allowlist in gateway services.py using
  get_app_config().get_model_config()
- Truncate model_name to 128 chars to match DB column constraint
- In worker.py, capture effective model name from agent.metadata after
  agent creation and persist if resolved differently than requested

* feat(run): add defense-in-depth model_name normalization and round-trip persistence tests

- Add _normalize_model_name() to RunRepository for whitespace stripping
  and 128-char truncation before DB writes.
- Add round-trip unit tests for model_name creation and default None
  in test_run_manager.py.

* fix(run): coerce non-string model_name values before strip/truncate in _normalize_model_name

* fix(gateway): add runtime type guard for model_name coercion in gateway services

Add isinstance check and str() coercion before calling .strip() to prevent
AttributeError when non-string types (int, None, etc.) flow through the
gateway. Paired with SQL integration test for end-to-end model_name
persistence across gateway → langgraph → persistence layer.

* fix(run): drop Alembic migration for model_name (no-op) and expose public update method on RunManager

- Drop a1b2c3d4e5f6 migration: model_name already exists in RunRow schema
  and is auto-created via Base.metadata.create_all() at startup
- Add update_model_name() public method to RunManager to replace the private
  _persist_to_store call in worker.py, preserving internal locking/persistence
This commit is contained in:
Yi Tang
2026-05-11 14:45:18 +01:00
committed by GitHub
parent 2eb11f97ab
commit de253e4a0a
8 changed files with 143 additions and 0 deletions
+51
View File
@@ -5,6 +5,7 @@ import re
import pytest
from deerflow.runtime import RunManager, RunStatus
from deerflow.runtime.runs.store.memory import MemoryRunStore
ISO_RE = re.compile(r"^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}")
@@ -141,3 +142,53 @@ async def test_create_defaults(manager: RunManager):
assert record.kwargs == {}
assert record.multitask_strategy == "reject"
assert record.assistant_id is None
@pytest.mark.anyio
async def test_model_name_create_or_reject():
"""create_or_reject should accept and persist model_name."""
from deerflow.runtime.runs.schemas import DisconnectMode
store = MemoryRunStore()
mgr = RunManager(store=store)
record = await mgr.create_or_reject(
"thread-1",
assistant_id="lead_agent",
on_disconnect=DisconnectMode.cancel,
metadata={"key": "val"},
kwargs={"input": {}},
multitask_strategy="reject",
model_name="anthropic.claude-sonnet-4-20250514-v1:0",
)
assert record.model_name == "anthropic.claude-sonnet-4-20250514-v1:0"
assert record.status == RunStatus.pending
# Verify model_name was persisted to store
stored = await store.get(record.run_id)
assert stored is not None
assert stored["model_name"] == "anthropic.claude-sonnet-4-20250514-v1:0"
# Verify retrieval returns the model_name via in-memory record
fetched = mgr.get(record.run_id)
assert fetched is not None
assert fetched.model_name == "anthropic.claude-sonnet-4-20250514-v1:0"
@pytest.mark.anyio
async def test_model_name_default_is_none():
"""create_or_reject without model_name should default to None."""
from deerflow.runtime.runs.schemas import DisconnectMode
store = MemoryRunStore()
mgr = RunManager(store=store)
record = await mgr.create_or_reject(
"thread-1",
on_disconnect=DisconnectMode.cancel,
model_name=None,
)
assert record.model_name is None
stored = await store.get(record.run_id)
assert stored["model_name"] is None