mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-12 23:12:23 -06:00
Patrick Buckley
530958e06b
Local lanes dropped the knob's graded value unless the operator declared
reasoning_effort_values (and, on the template channel, an effort key) —
picking Max sent a bare thinking toggle and the effort select
degenerated into seven positions that all meant 'on'. The user's
setting now always rides:
- openai-compatible: the flat reasoning_effort param carries the knob
verbatim (effort_passthrough on the lane default); declared values
still snap ordinally, and a declared effort_param still claims the
template channel and suppresses the flat param.
- anthropic-compatible: the graded value rides chat_template_kwargs
alongside the toggle whenever reasoning control is engaged — under
the operator's effort_param, else the conventional fallback key
(reasoning_effort); templates that don't reference the kwarg ignore
it. thinking_mode=none still injects nothing.
- Commercial lanes untouched: empty declared values still mean 'no
effort control' (o1-mini) and the ordinal snap is unchanged.
Golden writer now pins ensure_ascii=False: the baselines' literal em
dashes came from a hand edit (03f82521) the default-escaping writer
could never reproduce — regens no longer churn unrelated lines.
424 lines
15 KiB
Python
424 lines
15 KiB
Python
"""``GET /v1/api/models`` resolution-chain coverage.
|
|
|
|
The console handler resolves four defaults from settings + the enabled
|
|
model list:
|
|
|
|
* ``default_alias`` ← ``model.default_alias``
|
|
* ``channel_default_alias`` ← ``channels.default_model_alias``
|
|
* ``coordinator_default_alias`` ← ``coordinator.model_alias``, falling
|
|
back to ``default_alias`` when empty *or* pointing at a disabled /
|
|
removed alias (mirrors :mod:`turnstone.console.session_factory`).
|
|
* ``judge_default_alias`` ← ``judge.model``, falling back to the
|
|
resolved coordinator alias when empty *or* pointing at a value that
|
|
isn't an enabled alias. ``judge.model`` is alias-only — same
|
|
contract as the other model roles — and
|
|
:class:`turnstone.core.judge.IntentJudge` silently inherits the
|
|
session model when an unknown value is configured, so the API
|
|
surfaces the resolved coordinator alias rather than echoing the
|
|
misconfigured string.
|
|
|
|
These tests pin each branch so the home composer's resolved-alias
|
|
placeholder stays correct as the precedence rules evolve.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
from starlette.applications import Starlette
|
|
from starlette.middleware import Middleware
|
|
from starlette.routing import Route
|
|
from starlette.testclient import TestClient
|
|
|
|
from tests._coord_test_helpers import _AuthMiddleware, _FakeConfigStore
|
|
from turnstone.console.server import list_available_models
|
|
from turnstone.core.storage._sqlite import SQLiteBackend
|
|
|
|
|
|
@pytest.fixture
|
|
def storage(tmp_path: Any) -> SQLiteBackend:
|
|
return SQLiteBackend(str(tmp_path / "available_models.db"))
|
|
|
|
|
|
def _seed_model(
|
|
storage: SQLiteBackend,
|
|
*,
|
|
definition_id: str,
|
|
alias: str,
|
|
model: str = "model-x",
|
|
enabled: bool = True,
|
|
) -> None:
|
|
storage.create_model_definition(
|
|
definition_id=definition_id,
|
|
alias=alias,
|
|
model=model,
|
|
provider="openai-compatible",
|
|
base_url="http://localhost:8000/v1",
|
|
api_key="sk-test",
|
|
context_window=8192,
|
|
capabilities="{}",
|
|
enabled=enabled,
|
|
created_by="admin",
|
|
)
|
|
|
|
|
|
class _StubRegistry:
|
|
"""Mimics the surface ``resolve_coordinator_alias`` reads from
|
|
``coord_registry``: ``.default`` and ``.has_alias()``.
|
|
|
|
Production wires this through ``ModelRegistry``, which in turn
|
|
pulls aliases from both DB rows and config.toml. The fixture
|
|
mirrors the storage's enabled-row set so ``has_alias()`` agrees
|
|
with what the placeholder's enabled-row filter would accept —
|
|
without that alignment the helper rejects every tier-2 candidate
|
|
and the placeholder goes blank in cases that production handles
|
|
fine."""
|
|
|
|
def __init__(self, *, default: str, known: set[str]) -> None:
|
|
self.default = default
|
|
self._known = known
|
|
|
|
def has_alias(self, alias: str) -> bool:
|
|
return alias in self._known
|
|
|
|
|
|
def _make_client(
|
|
storage: SQLiteBackend,
|
|
*,
|
|
settings: dict[str, str] | None = None,
|
|
registry_default: str = "",
|
|
config_store: bool = True,
|
|
) -> TestClient:
|
|
app = Starlette(
|
|
routes=[Route("/v1/api/models", list_available_models)],
|
|
middleware=[Middleware(_AuthMiddleware)],
|
|
)
|
|
app.state.auth_storage = storage
|
|
if config_store:
|
|
app.state.config_store = _FakeConfigStore(dict(settings or {}))
|
|
# ``coord_registry`` is always set in production after lifespan
|
|
# startup; mirror that here. ``has_alias`` answers from the same
|
|
# enabled-rows set the handler filters against.
|
|
enabled = {r["alias"] for r in storage.list_model_definitions(enabled_only=True)}
|
|
app.state.coord_registry = _StubRegistry(default=registry_default, known=enabled)
|
|
client = TestClient(app)
|
|
client.headers.update({"X-Test-User": "admin", "X-Test-Perms": ""})
|
|
return client
|
|
|
|
|
|
def _get_models(client: TestClient) -> dict[str, Any]:
|
|
resp = client.get("/v1/api/models")
|
|
assert resp.status_code == 200, resp.text
|
|
return resp.json()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Coordinator resolution
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_no_settings_leaves_all_defaults_blank(storage: SQLiteBackend) -> None:
|
|
"""No model.default_alias, no per-role overrides → every default
|
|
field is empty and ``models`` is an empty list."""
|
|
body = _get_models(_make_client(storage))
|
|
assert body == {
|
|
"models": [],
|
|
"default_alias": "",
|
|
"channel_default_alias": "",
|
|
"coordinator_default_alias": "",
|
|
"judge_default_alias": "",
|
|
}
|
|
|
|
|
|
def test_coordinator_inherits_default_alias_when_unset(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
body = _get_models(_make_client(storage, settings={"model.default_alias": "primary"}))
|
|
assert body["default_alias"] == "primary"
|
|
assert body["coordinator_default_alias"] == "primary"
|
|
|
|
|
|
def test_coordinator_explicit_enabled_alias_passes_through(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
_seed_model(storage, definition_id="m2", alias="fast")
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"coordinator.model_alias": "fast",
|
|
},
|
|
)
|
|
)
|
|
assert body["coordinator_default_alias"] == "fast"
|
|
|
|
|
|
def test_coordinator_set_to_disabled_alias_falls_back_to_default(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""Operator disabled the alias the coordinator was pinned to —
|
|
fall back to the registry default rather than advertising a model
|
|
that workstream creation would refuse to use."""
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
_seed_model(storage, definition_id="m2", alias="legacy", enabled=False)
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"coordinator.model_alias": "legacy",
|
|
},
|
|
)
|
|
)
|
|
assert body["coordinator_default_alias"] == "primary"
|
|
|
|
|
|
def test_coordinator_set_to_unknown_alias_falls_back_to_default(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"coordinator.model_alias": "ghost",
|
|
},
|
|
)
|
|
)
|
|
assert body["coordinator_default_alias"] == "primary"
|
|
|
|
|
|
def test_coordinator_falls_back_to_registry_default_when_config_store_empty(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""Match ``console/session_factory.py:109-110``: when both
|
|
``coordinator.model_alias`` and ``model.default_alias`` are unset, new
|
|
coordinator sessions run on ``registry.default`` (loaded from
|
|
config.toml ``[model].default``). The placeholder must report the
|
|
same alias rather than going blank — otherwise the home composer
|
|
advertises "Default model" while sessions actually launch on a
|
|
concrete alias."""
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
body = _get_models(_make_client(storage, registry_default="primary"))
|
|
assert body["default_alias"] == ""
|
|
assert body["coordinator_default_alias"] == "primary"
|
|
assert body["judge_default_alias"] == "primary"
|
|
|
|
|
|
def test_coordinator_skips_registry_default_when_alias_disabled(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""Registry default points at an alias that's been disabled in the DB
|
|
— the placeholder stays blank rather than advertising a model that
|
|
workstream creation would refuse to use."""
|
|
_seed_model(storage, definition_id="m1", alias="legacy", enabled=False)
|
|
body = _get_models(_make_client(storage, registry_default="legacy"))
|
|
assert body["coordinator_default_alias"] == ""
|
|
|
|
|
|
def test_coordinator_falls_back_to_registry_default_when_config_store_missing(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""Edge case from PR #500 review: lifespan can leave
|
|
``app.state.config_store`` as None (e.g. a startup exception) while
|
|
``coord_registry`` still binds successfully. The placeholder must
|
|
still advertise ``registry.default`` (filtered against enabled rows)
|
|
rather than going blank — otherwise the home composer is uselessly
|
|
empty in a degraded-but-recoverable state."""
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
body = _get_models(_make_client(storage, registry_default="primary", config_store=False))
|
|
assert body["default_alias"] == ""
|
|
assert body["coordinator_default_alias"] == "primary"
|
|
assert body["judge_default_alias"] == "primary"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Judge resolution
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_judge_empty_inherits_resolved_coordinator_alias(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
_seed_model(storage, definition_id="m2", alias="fast")
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"coordinator.model_alias": "fast",
|
|
},
|
|
)
|
|
)
|
|
assert body["coordinator_default_alias"] == "fast"
|
|
assert body["judge_default_alias"] == "fast"
|
|
|
|
|
|
def test_judge_explicit_enabled_alias_passes_through(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
_seed_model(storage, definition_id="m2", alias="judge-fast")
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"judge.model": "judge-fast",
|
|
},
|
|
)
|
|
)
|
|
assert body["judge_default_alias"] == "judge-fast"
|
|
|
|
|
|
def test_judge_set_to_unknown_value_inherits_coordinator(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""``judge.model`` is alias-only — same contract as the other model
|
|
roles. An unknown value silently inherits the session model in
|
|
:class:`IntentJudge`, so the API surfaces the resolved coordinator
|
|
alias rather than echoing the misconfigured string."""
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"judge.model": "anthropic/claude-haiku-4-5", # raw, not an alias
|
|
},
|
|
)
|
|
)
|
|
assert body["coordinator_default_alias"] == "primary"
|
|
assert body["judge_default_alias"] == "primary"
|
|
|
|
|
|
def test_judge_set_to_disabled_alias_inherits_coordinator(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""Disabled-alias case is handled identically to the unknown-value
|
|
case — both trip the alias-not-resolved path."""
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
_seed_model(storage, definition_id="m2", alias="judge-old", enabled=False)
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={
|
|
"model.default_alias": "primary",
|
|
"judge.model": "judge-old",
|
|
},
|
|
)
|
|
)
|
|
assert body["judge_default_alias"] == "primary"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Pre-existing fields stay correct under the new resolution code
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_channel_default_alias_blanked_when_disabled(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
_seed_model(storage, definition_id="m1", alias="primary", enabled=False)
|
|
body = _get_models(
|
|
_make_client(
|
|
storage,
|
|
settings={"channels.default_model_alias": "primary"},
|
|
)
|
|
)
|
|
assert body["channel_default_alias"] == ""
|
|
|
|
|
|
def test_models_payload_strips_secret_fields(storage: SQLiteBackend) -> None:
|
|
"""Regression guard: only alias/model/provider (+ the derived
|
|
effort_ladder) land in the response, never api_key / base_url /
|
|
context_window / raw capabilities."""
|
|
_seed_model(storage, definition_id="m1", alias="primary")
|
|
body = _get_models(_make_client(storage))
|
|
assert len(body["models"]) == 1
|
|
entry = body["models"][0]
|
|
assert set(entry) == {"alias", "model", "provider", "effort_ladder"}
|
|
assert entry["alias"] == "primary"
|
|
assert entry["model"] == "model-x"
|
|
assert entry["provider"] == "openai-compatible"
|
|
|
|
|
|
def test_effort_ladder_parses_string_capabilities(storage: SQLiteBackend) -> None:
|
|
"""The capabilities column is a JSON STRING — the ladder must survive
|
|
the parse (regression: .items() on the raw string threw and the
|
|
guard silently dropped the field from every row)."""
|
|
storage.create_model_definition(
|
|
definition_id="m1",
|
|
alias="qwen",
|
|
model="qwen3.6-27b",
|
|
provider="anthropic-compatible",
|
|
base_url="http://localhost:8000",
|
|
api_key="dummy",
|
|
context_window=262144,
|
|
capabilities='{"thinking_mode": "manual", "thinking_param": "enable_thinking"}',
|
|
enabled=True,
|
|
created_by="admin",
|
|
)
|
|
body = _get_models(_make_client(storage))
|
|
ladder = {r["value"]: r["effective"] for r in body["models"][0]["effort_ladder"]}
|
|
assert ladder["none"] == "off"
|
|
assert ladder["medium"] == "on+medium"
|
|
assert ladder["max"] == "on+max"
|
|
|
|
|
|
def test_effort_ladder_key_survives_malformed_capabilities(
|
|
storage: SQLiteBackend,
|
|
) -> None:
|
|
"""A capabilities column that fails to parse must not drop the key —
|
|
every row carries ``effort_ladder`` (empty on failure) so clients can
|
|
index it unconditionally instead of null-checking per row."""
|
|
storage.create_model_definition(
|
|
definition_id="m1",
|
|
alias="broken",
|
|
model="model-x",
|
|
provider="openai-compatible",
|
|
base_url="http://localhost:8000/v1",
|
|
api_key="dummy",
|
|
context_window=131072,
|
|
capabilities="{not valid json",
|
|
enabled=True,
|
|
created_by="admin",
|
|
)
|
|
body = _get_models(_make_client(storage))
|
|
entry = body["models"][0]
|
|
assert set(entry) == {"alias", "model", "provider", "effort_ladder"}
|
|
assert entry["effort_ladder"] == []
|
|
|
|
|
|
def test_effort_ladder_honors_responses_api_surface(storage: SQLiteBackend) -> None:
|
|
"""server_compat.api_surface (namespaced inside the capabilities JSON)
|
|
switches the projection to the flat-param path — no template toggle."""
|
|
caps = (
|
|
'{"thinking_mode": "manual", "thinking_param": "enable_thinking",'
|
|
' "reasoning_effort_values": ["low", "medium", "high"],'
|
|
' "server_compat": {"api_surface": "responses"}}'
|
|
)
|
|
storage.create_model_definition(
|
|
definition_id="m1",
|
|
alias="mistral",
|
|
model="mistral-medium",
|
|
provider="openai-compatible",
|
|
base_url="http://localhost:8000/v1",
|
|
api_key="dummy",
|
|
context_window=131072,
|
|
capabilities=caps,
|
|
enabled=True,
|
|
created_by="admin",
|
|
)
|
|
body = _get_models(_make_client(storage))
|
|
ladder = {r["value"]: r["effective"] for r in body["models"][0]["effort_ladder"]}
|
|
# Responses surface: flat param only — no "on+"/"off" toggle tokens.
|
|
assert ladder["medium"] == "medium"
|
|
assert ladder["none"] == "default"
|