chore: 移除智谱 GLM 供应商(GLM 模型 + CogView/CogVideoX 媒体 + 契约代码/前端/文档/测试全清)

This commit is contained in:
api-gateway committed 2026-09-18 09:50:26 +08:00
1 parent d838763f35
commit a7e2692dec
16 files changed
+79 -288

No files matched your search

+17 -42
View File
@@ -89,31 +89,8 @@ def _login_admin_session(client=None):
# ── 配置加载 ──
def test_load_config_providers():
cfg = load_config(CONFIG)
assert set(cfg.providers.keys()) == {"agnes", "volc_engine", "bigmodel"}
assert set(cfg.providers.keys()) == {"agnes", "volc_engine"}
assert cfg.providers["agnes"].models[0].id == "agnes-3.0-flash"
# 智谱:base_url + token_env + 6 个模型 + V 型号视觉标记
assert cfg.providers["bigmodel"].base_url == "https://open.bigmodel.cn/api/paas/v4"
assert cfg.providers["bigmodel"].auth.token_env == "ZHIPU_API_KEY"
bm = cfg.providers["bigmodel"]
text_ids = [m.id for m in bm.models if m.type == "text"]
assert text_ids == ["GLM-4.7-Flash", "GLM-4-Flash-250414", "GLM-Z1-Flash",
"GLM-4.6V-Flash", "GLM-4V-Flash", "GLM-4.1V-Thinking-Flash"]
# 智谱媒体模型:cogview-3-flash(图像)、cogvideox-flash(视频)
assert [m.id for m in bm.models if m.type == "image"] == ["cogview-3-flash"]
assert [m.id for m in bm.models if m.type == "video"] == ["cogvideox-flash"]
for m in bm.models:
if m.type != "text":
continue
want = m.id in ("GLM-4.6V-Flash", "GLM-4V-Flash", "GLM-4.1V-Thinking-Flash")
assert m.vision is want, f"{m.id} vision 应为 {want}"
# 智谱媒体契约(图像像素档 + 视频 zhipu 异步风格)
md = bm.media
assert md.supports_image and md.supports_video
assert md.image_default_size == "1024x1024"
assert md.video_style == "zhipu"
assert md.video_default_size == "1920x1080"
assert md.video_create_endpoint == "/videos/generations"
assert md.video_poll_path == "/async-result"
def test_load_config_routes():
@@ -333,7 +310,7 @@ def test_resolve_media_model_via_route_alias():
# wjd 路由链里第 2 个是 agnes-3.0-flash(text),但 image 模型不在这条链 → 走别名找不到 image
# 单独构造一条指向 image 的路由来验证别名解析逻辑
from app.config import RouteInfo
cfg.routes["img"] = RouteInfo(name="img", models=["GLM-4.1V-Thinking-Flash", "agnes-image-2.5-flash"])
cfg.routes["img"] = RouteInfo(name="img", models=["agnes-3.0-flash", "agnes-image-2.5-flash"])
res = m._resolve_media_model(cfg, "img", "image")
assert res is not None and res[4] == "agnes-image-2.5-flash"
@@ -2256,9 +2233,8 @@ def test_video_polls_merged_into_one_log_row_with_response():
"prompt": "x", "aspect_ratio": "16:9"}, headers=ah)
assert r.status_code == 200, r.text
vid = r.json()["video_id"]
poll_q = f"/v1/videos/{vid}?model=agnes-video-2.5-flash" # 多视频供应商(agnes+智谱)时必须显式指定 model
client.get(poll_q, headers=ah) # 第 1 次轮询 processing
client.get(poll_q, headers=ah) # 第 2 次轮询 completed
client.get(f"/v1/videos/{vid}", headers=ah) # 第 1 次轮询 processing
client.get(f"/v1/videos/{vid}", headers=ah) # 第 2 次轮询 completed
logs = client.get("/logs?n=200", headers=ah).json()["entries"]
rows = [e for e in logs if e.get("video_id") == vid]
assert len(rows) == 1, f"轮询应合成到创建那条里(实际 {len(rows)} 行): {[r['path'] for r in logs]}"
@@ -2318,7 +2294,7 @@ def test_wjd_route_orders_by_availability_and_speed():
from app.config import RouteInfo
from app.circuit import CircuitBreakerRegistry
import app.main as m
saved = {k: os.environ.get(k) for k in ("AGNES_API_KEY", "VOLC_API_KEY", "ZHIPU_API_KEY")}
saved = {k: os.environ.get(k) for k in ("AGNES_API_KEY", "VOLC_API_KEY")}
for k in saved:
os.environ[k] = "test-token"
orig_m, orig_c = m._metrics, m._circuits
@@ -2328,22 +2304,21 @@ def test_wjd_route_orders_by_availability_and_speed():
cfg = m._cfg()
cfg.routes["wjd_speedtest"] = RouteInfo(
name="wjd_speedtest",
models=["ark-code-latest", "agnes-3.0-flash", "GLM-4.7-Flash"], # 配置优先级 volc>agnes>bigmodel
models=["ark-code-latest", "agnes-3.0-flash"], # 配置优先级 volc>agnes
retry=1)
try:
# 冷启动:没有任何延迟样本 → 保持配置顺序
assert m._route_chain(cfg, "wjd_speedtest")[0] == [
"ark-code-latest", "agnes-3.0-flash", "GLM-4.7-Flash"]
# 喂速度:agnes 最快、bigmodel 次之、volc 最慢 → 完全重排
"ark-code-latest", "agnes-3.0-flash"]
# 喂速度:agnes 快、volc 慢 → 完全重排
m._metrics.record_latency("agnes-3.0-flash", 0.5)
m._metrics.record_latency("GLM-4.7-Flash", 1.5)
m._metrics.record_latency("ark-code-latest", 4.0)
assert m._route_chain(cfg, "wjd_speedtest")[0] == [
"agnes-3.0-flash", "GLM-4.7-Flash", "ark-code-latest"]
"agnes-3.0-flash", "ark-code-latest"]
# 最快那个供应商熔断开 → 排到最后,次快上位(未测速的可用模型才用探测位兜底)
m._circuits.get("agnes")._state = "open"
chain2 = m._route_chain(cfg, "wjd_speedtest")[0]
assert chain2[0] == "GLM-4.7-Flash", chain2
assert chain2[0] == "ark-code-latest", chain2
assert chain2[-1] == "agnes-3.0-flash", chain2
finally:
m._metrics, m._circuits = orig_m, orig_c
@@ -2556,9 +2531,9 @@ def test_vision_first_reorders_only_when_vision_exists():
"""带图请求:链上有视觉模型才重排(提到最前),一个都没有就别动(不掩盖能力缺失)。"""
import app.main as m
cfg = load_config(CONFIG)
assert m._vision_first(cfg, ["ark-code-latest", "agnes-3.0-flash", "GLM-Z1-Flash"]) == \
["agnes-3.0-flash", "ark-code-latest", "GLM-Z1-Flash"], "视觉模型提到最前,其余保持相对顺序"
assert m._vision_first(cfg, ["ark-code-latest", "GLM-Z1-Flash"]) == ["ark-code-latest", "GLM-Z1-Flash"]
assert m._vision_first(cfg, ["ark-code-latest", "agnes-3.0-flash"]) == \
["agnes-3.0-flash", "ark-code-latest"], "视觉模型提到最前,其余保持相对顺序"
assert m._vision_first(cfg, ["ark-code-latest"]) == ["ark-code-latest"]
def test_messages_have_images_detects_vision_blocks():
@@ -3564,7 +3539,7 @@ def test_config_save_applies_without_restart():
view["server"]["timeout"] = 95
view["server"]["retry"] = 2
view["observability"]["access_log_maxlen"] = 777
view["routes"]["wjd"]["models"] = ["GLM-4.1V-Thinking-Flash", "ark-code-latest"]
view["routes"]["wjd"]["models"] = ["agnes-3.0-flash", "ark-code-latest"]
view["providers"]["volc_engine"]["models"].append(
{"id": "ark-code-mini", "display_name": "迷你", "type": "text", "vision": False})
view["pricing"]["per_model"]["ark-code-mini"] = {"input": 0.1, "output": 0.2}
@@ -3578,17 +3553,17 @@ def test_config_save_applies_without_restart():
assert m.config.server.timeout == 95
assert m.config.server.retry == 2
assert m.config.observability.access_log_maxlen == 777
assert m.config.routes["wjd"].models == ["GLM-4.1V-Thinking-Flash", "ark-code-latest"]
assert m.config.routes["wjd"].models == ["agnes-3.0-flash", "ark-code-latest"]
assert m.config.find_provider_for_model("ark-code-mini")[0] == "volc_engine"
assert m._access._max == 777, "访问日志容量应就地调整"
# 盘上也变了,且旧文件有备份
on_disk = _yaml.safe_load(cfg_path.read_text(encoding="utf-8"))
assert on_disk["server"]["timeout"] == 95
assert on_disk["routes"]["wjd"]["models"] == ["GLM-4.1V-Thinking-Flash", "ark-code-latest"]
assert on_disk["routes"]["wjd"]["models"] == ["agnes-3.0-flash", "ark-code-latest"]
assert (P(tmp.name) / "gateway.yaml.bak").exists(), "保存前应备份原文件"
# 路由链顺序变更后,/v1/models 立刻跟着变(页面/调用方看到的就是新顺序)
lm = client.get("/v1/models", headers=ah).json()
assert [x for x in lm["data"] if x["type"] == "route"][0]["models"][:2] == ["GLM-4.1V-Thinking-Flash", "ark-code-latest"]
assert [x for x in lm["data"] if x["type"] == "route"][0]["models"][:2] == ["agnes-3.0-flash", "ark-code-latest"]
# ② 改"需重启"的键:能保存,但要明确回提示(不能假装已生效)
assert _yaml.safe_load(cfg_path.read_text(encoding="utf-8"))["server"]["port"] == 8808