mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-26 21:26:39 +00:00
bcaf6db36a
* feat(models): add declarative reasoning capability contract (#5073) Introduce an optional per-model `reasoning:` block beside the legacy `supports_thinking` / `supports_reasoning_effort` booleans. It declares thinking availability (unsupported | optional | required), the accepted effort values with aliases, default, and serialization path, the payload dialect, and the reasoning-history requirement. When present the booleans are derived from it and contradictory profiles fail at config load. `deerflow.models.reasoning` normalizes legacy and declared profiles into one immutable contract and resolves every caller's generic request against it. `create_chat_model` is the single enforcement point: required-thinking models never receive a synthesized disable payload, unsupported effort values never reach the provider, and the dialect synthesizes the on/off payload when no template exists. Legacy profiles keep the historical path byte-for-byte. The lead agent and subagent descriptor resolve the same policy first so run metadata reports effective values. `/api/models` and `DeerFlowClient` project the contract as `reasoning`; the frontend derives mode clamping and effort choices from it through `core/models/reasoning.ts`, and user preferences accept provider-specific effort tokens. The setup wizard's Z.AI GLM-5.3-Flash profile migrates to the contract, restoring its low/high/max effort control. * docs(models): move the reasoning contract guidance into models/AGENTS.md backend/AGENTS.md sits within 46 bytes of the 96 KiB effective-chain hard limit for the middlewares, runtime, sandbox, and subagents guides, so the new section pushed scripts/check_agent_guidance.py over it. The models guide is the nearest file for the factory and the contract module, and its chain has ample room. * fix(models): address review on the reasoning contract - vLLM dialect: the enable path now mirrors whichever chat_template_kwargs switch the template declares, like the disable path already did, so a template using the older `thinking` key no longer also grows `enable_thinking`. - Validate operator-supplied effort values at `effort.path` inside `when_thinking_enabled`, `when_thinking_disabled`, and the `thinking` shortcut against the contract, not only the profile-level value; they are forwarded when the caller chooses nothing, so the "unknown values never reach the provider" guarantee now holds for them too. - Constrain `effort.path` to dotted identifiers and reject single-segment paths that would replace a whole mapping (`extra_body`, `thinking`, `model_kwargs`, `default_headers`, `default_query`). - Z.AI GLM-5.3-Flash profile: `default: high` instead of `max`, because the default also governs summarization, title generation, and subagent calls that never choose an effort; `max` stays selectable. Documented in the config example, the configuration manual, and the design note. * fix(models): close reasoning contract review gaps * fix(models): preserve native Ollama reasoning config * fix(models): keep native reasoning strings and project reasoning into the descriptor - `ModelConfig.reasoning` also accepts the level string ChatOllama takes for gpt-oss style models (`low` / `medium` / `high`); the factory forwards both the boolean and the string on the legacy path, so profiles that passed `reasoning: high` through before the contract field existed keep loading and keep sending it. - The assembly descriptor no longer excludes `reasoning` from `model_parameters`: the native ChatOllama value and a declared contract's dialect/history/effort change the request payload, so they now move the assembly fingerprint. - e2e: the sidecar spec pinned the pre-contract body where a model without effort control still received `reasoning_effort: minimal`; the preset is now dropped for such models (the Gateway discarded it anyway), so the assertion expects the key to be absent.
94 lines
3.4 KiB
Python
94 lines
3.4 KiB
Python
"""``/api/models`` projects the normalized reasoning contract beside the legacy booleans (issue #5073)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
from fastapi import FastAPI
|
|
from fastapi.testclient import TestClient
|
|
|
|
from app.gateway.routers import models as models_router
|
|
from deerflow.config.app_config import AppConfig
|
|
from deerflow.config.authorization_config import AuthorizationConfig
|
|
from deerflow.config.model_config import ModelConfig
|
|
from deerflow.config.sandbox_config import SandboxConfig
|
|
from deerflow.config.token_usage_config import TokenUsageConfig
|
|
|
|
|
|
def _app_config(models: list[ModelConfig]) -> AppConfig:
|
|
return AppConfig(
|
|
models=models,
|
|
sandbox=SandboxConfig(use="deerflow.sandbox.local:LocalSandboxProvider"),
|
|
token_usage=TokenUsageConfig(enabled=False),
|
|
authorization=AuthorizationConfig(),
|
|
)
|
|
|
|
|
|
def _legacy_model() -> ModelConfig:
|
|
return ModelConfig(name="legacy", model="legacy", use="langchain_openai:ChatOpenAI", supports_thinking=True, supports_reasoning_effort=True)
|
|
|
|
|
|
def _contract_model() -> ModelConfig:
|
|
return ModelConfig(
|
|
name="glm-5.3-flash",
|
|
model="glm-5.3-flash",
|
|
use="deerflow.models.patched_deepseek:PatchedChatDeepSeek",
|
|
reasoning={
|
|
"thinking": "required",
|
|
"dialect": "openai_extra_body",
|
|
"history": "clear",
|
|
"effort": {"values": ["low", "high", "max"], "default": "max", "aliases": {"minimal": "low", "medium": "high"}},
|
|
},
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def client(monkeypatch):
|
|
config = AuthorizationConfig(enabled=False)
|
|
monkeypatch.setattr("app.gateway.authz._get_route_authorization_config", lambda: config)
|
|
monkeypatch.setattr("app.gateway.routers.models.get_optional_user_from_request", AsyncMock(return_value=None))
|
|
|
|
app = FastAPI()
|
|
app.include_router(models_router.router)
|
|
app.dependency_overrides[models_router.get_config] = lambda: _app_config([_legacy_model(), _contract_model()])
|
|
with TestClient(app) as test_client:
|
|
yield test_client
|
|
|
|
|
|
def test_list_models_projects_reasoning_for_every_model(client):
|
|
response = client.get("/api/models")
|
|
|
|
assert response.status_code == 200
|
|
by_name = {m["name"]: m for m in response.json()["models"]}
|
|
|
|
legacy = by_name["legacy"]
|
|
assert legacy["supports_thinking"] is True
|
|
assert legacy["supports_reasoning_effort"] is True
|
|
assert legacy["reasoning"] == {
|
|
"thinking": "optional",
|
|
"effort": {"values": ["minimal", "low", "medium", "high"], "default": None, "aliases": {}},
|
|
"history": None,
|
|
"source": "legacy",
|
|
}
|
|
|
|
contract = by_name["glm-5.3-flash"]
|
|
# Deprecation-window projection: the booleans are derived from the contract.
|
|
assert contract["supports_thinking"] is True
|
|
assert contract["supports_reasoning_effort"] is True
|
|
assert contract["reasoning"] == {
|
|
"thinking": "required",
|
|
"effort": {"values": ["low", "high", "max"], "default": "max", "aliases": {"minimal": "low", "medium": "high"}},
|
|
"history": "clear",
|
|
"source": "contract",
|
|
}
|
|
|
|
|
|
def test_get_model_projects_reasoning(client):
|
|
response = client.get("/api/models/glm-5.3-flash")
|
|
|
|
assert response.status_code == 200
|
|
body = response.json()
|
|
assert body["reasoning"]["thinking"] == "required"
|
|
assert body["reasoning"]["effort"]["values"] == ["low", "high", "max"]
|