feat(aibox): L-batch profile polish (display name, prefix escape, temperature, reasoning aliases)
L1 display name: client.name now resolves to the profile's display_name field, falling back to the profile key — the dialogue context no longer labels Kimi/Qwen sessions "DeepSeek". The legacy flat api section keeps "DeepSeek" (zero breakage). _resolve_model_profile now returns (profile, model, profile_name). L2 prefix escape: "model:NAME" forces bare-model semantics even when a profile happens to be named NAME; "profile:NAME" forces profile semantics and raises a clear error (listing available profiles) when missing, instead of silently falling back to bare-name behavior. Empty prefixes are rejected. Wired through --model / create_llm_client / subagent model params. L3 profile temperature: new profile field "temperature" becomes the client's default_temperature. chat_completion/stream_chat treat temperature=None as "use profile default, else the old hardcoded 0.3/0.7", so explicit caller values still win. DeepSeekChat and run_light_subagent resolve CLI > profile > constants.DEFAULT_TEMPERATURE. L5 reasoning field aliases: _parse_delta recognizes reasoning_content / reasoning / thinking / thinking_content (first non-empty wins), so non-DeepSeek vendors' thinking streams are no longer silently dropped. L4 (cross-profile failover) intentionally deferred: streaming failover needs request-replay semantics and is feature-level work. Tests: new TestLBatch (16 cases); 7 existing unpack sites updated to the 3-tuple. Full suite 315 passed.
This commit is contained in:
qing committed
1 parent
a583f44d5d
commit
d29bb5504a
4 files changed
+265
-36
No files matched your search
@@ -88,33 +88,38 @@ def _cfg(models=MODELS, default_model="deepseek", **api_over):
|
||||
class TestResolveProfile:
|
||||
def test_explicit_profile_name(self):
|
||||
"""model=档案名 → 完整采用该档案，模型名取档案内 model"""
|
||||
profile, model = _resolve_model_profile(_cfg(), "kimi")
|
||||
profile, model, pname = _resolve_model_profile(_cfg(), "kimi")
|
||||
assert profile is MODELS["kimi"]
|
||||
assert model == "kimi-k2"
|
||||
assert pname == "kimi"
|
||||
|
||||
def test_bare_model_name_uses_default_profile(self):
|
||||
"""model=裸名 → 默认档案端点 + 裸名作为模型名"""
|
||||
profile, model = _resolve_model_profile(_cfg(), "deepseek-v3-legacy")
|
||||
profile, model, pname = _resolve_model_profile(_cfg(), "deepseek-v3-legacy")
|
||||
assert profile is MODELS["deepseek"]
|
||||
assert model == "deepseek-v3-legacy"
|
||||
assert pname == "deepseek"
|
||||
|
||||
def test_no_model_uses_default_profile(self):
|
||||
"""未指定 model → 默认档案与档案内模型名"""
|
||||
profile, model = _resolve_model_profile(_cfg(), None)
|
||||
profile, model, pname = _resolve_model_profile(_cfg(), None)
|
||||
assert profile is MODELS["deepseek"]
|
||||
assert model == "deepseek-v4-flash"
|
||||
assert pname == "deepseek"
|
||||
|
||||
def test_fallback_when_no_models_section(self):
|
||||
"""无 models 节 → (None, model) 回退旧 api 扁平节"""
|
||||
profile, model = _resolve_model_profile(_cfg(models=None), "anything")
|
||||
profile, model, pname = _resolve_model_profile(_cfg(models=None), "anything")
|
||||
assert profile is None
|
||||
assert model == "anything"
|
||||
assert pname is None
|
||||
|
||||
def test_fallback_when_default_model_missing(self):
|
||||
"""default_model 指向不存在的档案且 model 未命中 → 回退"""
|
||||
profile, model = _resolve_model_profile(_cfg(default_model="nope"), "whatever")
|
||||
profile, model, pname = _resolve_model_profile(_cfg(default_model="nope"), "whatever")
|
||||
assert profile is None
|
||||
assert model == "whatever"
|
||||
assert pname is None
|
||||
|
||||
|
||||
# ==================== create_llm_client 档案构造 ====================
|
||||
@@ -279,7 +284,7 @@ class TestH2SchemaValidation:
|
||||
def test_default_profile_missing_model_bare_name_ok(self):
|
||||
"""默认档案缺 model + 传裸模型名 → 裸名补位，合法"""
|
||||
models = {"deepseek": {"api_url": "https://api.deepseek.com/chat/completions"}}
|
||||
profile, model = _resolve_model_profile(_cfg(models=models), "deepseek-v4-lite")
|
||||
profile, model, _ = _resolve_model_profile(_cfg(models=models), "deepseek-v4-lite")
|
||||
assert profile is models["deepseek"]
|
||||
assert model == "deepseek-v4-lite"
|
||||
|
||||
@@ -526,6 +531,159 @@ def constants_reasoning_default():
|
||||
return constants.REASONING_ENABLED
|
||||
|
||||
|
||||
# ==================== L 批：展示名/前缀逃逸/档案温度/思考字段别名 ====================
|
||||
|
||||
class TestLBatch:
|
||||
"""L1 展示名 / L2 model:-profile: 前缀逃逸 / L3 档案级 temperature / L5 思考流字段别名"""
|
||||
|
||||
# ---------- L1：client.name 按档案展示 ----------
|
||||
|
||||
def test_l1_name_is_profile_name(self):
|
||||
"""档案命中 → client.name = 档案名（不再恒为 DeepSeek）"""
|
||||
with mock.patch.dict(os.environ, {"MOONSHOT_API_KEY": "sk-moon"}):
|
||||
c = create_llm_client(_cfg(), model="kimi")
|
||||
assert c.name == "kimi"
|
||||
|
||||
def test_l1_display_name_override(self):
|
||||
"""档案 display_name 字段 > 档案名"""
|
||||
models = dict(MODELS)
|
||||
models["kimi"] = dict(models["kimi"], display_name="Kimi K2")
|
||||
with mock.patch.dict(os.environ, {"MOONSHOT_API_KEY": "sk-moon"}):
|
||||
c = create_llm_client(_cfg(models=models), model="kimi")
|
||||
assert c.name == "Kimi K2"
|
||||
|
||||
def test_l1_flat_api_keeps_deepseek(self):
|
||||
"""旧扁平节（无档案）→ name 保持 DeepSeek（零破坏）"""
|
||||
with mock.patch.dict(os.environ, {"DEEPSEEK_API_KEY": "sk-ds"}):
|
||||
c = create_llm_client(_cfg(models=None))
|
||||
assert c.name == "DeepSeek"
|
||||
|
||||
def test_l1_bare_name_uses_default_profile_name(self):
|
||||
"""裸模型名走默认档案 → name = 默认档案名"""
|
||||
with mock.patch.dict(os.environ, {"DEEPSEEK_API_KEY": "sk-ds"}):
|
||||
c = create_llm_client(_cfg(), model="deepseek-v4-lite")
|
||||
assert c.name == "deepseek"
|
||||
|
||||
# ---------- L2：前缀逃逸 ----------
|
||||
|
||||
def test_l2_model_prefix_forces_bare(self):
|
||||
"""档案恰好叫 deepseek-chat 时 model:deepseek-chat 仍走裸名语义"""
|
||||
models = {
|
||||
"deepseek-chat": dict(MODELS["deepseek"]),
|
||||
"kimi": dict(MODELS["kimi"]),
|
||||
}
|
||||
profile, model, pname = _resolve_model_profile(
|
||||
_cfg(models=models, default_model="kimi"), "model:deepseek-chat")
|
||||
assert profile is models["kimi"] # 默认档案端点
|
||||
assert model == "deepseek-chat" # 裸名作模型名
|
||||
assert pname == "kimi"
|
||||
|
||||
def test_l2_profile_prefix_forces_profile(self):
|
||||
"""profile:kimi 强制档案语义（即便存在同名裸模型的歧义）"""
|
||||
profile, model, pname = _resolve_model_profile(_cfg(), "profile:kimi")
|
||||
assert profile is MODELS["kimi"]
|
||||
assert model == "kimi-k2"
|
||||
assert pname == "kimi"
|
||||
|
||||
def test_l2_profile_prefix_missing_raises(self):
|
||||
"""profile:不存在的档案 → 明确报错（不再静默落回裸名语义）"""
|
||||
with pytest.raises(ValueError, match="不存在"):
|
||||
_resolve_model_profile(_cfg(), "profile:nonexistent")
|
||||
|
||||
def test_l2_empty_prefix_raises(self):
|
||||
"""前缀后为空 → 报错"""
|
||||
with pytest.raises(ValueError, match="前缀后为空"):
|
||||
_resolve_model_profile(_cfg(), "model:")
|
||||
with pytest.raises(ValueError, match="前缀后为空"):
|
||||
_resolve_model_profile(_cfg(), "profile:")
|
||||
|
||||
def test_l2_prefix_via_create_client(self):
|
||||
"""端到端：--model model:NAME / profile:NAME 经 create_llm_client 生效"""
|
||||
with mock.patch.dict(os.environ, {"MOONSHOT_API_KEY": "sk-moon",
|
||||
"DEEPSEEK_API_KEY": "sk-ds"}):
|
||||
c1 = create_llm_client(_cfg(), model="model:deepseek-v4-lite")
|
||||
assert c1.model == "deepseek-v4-lite" and c1.name == "deepseek"
|
||||
c2 = create_llm_client(_cfg(), model="profile:kimi")
|
||||
assert c2.model == "kimi-k2" and c2.name == "kimi"
|
||||
|
||||
# ---------- L3：档案级 temperature ----------
|
||||
|
||||
def test_l3_profile_temperature_default(self):
|
||||
"""档案 temperature → client.default_temperature；chat_completion 未传参时生效"""
|
||||
models = dict(MODELS)
|
||||
models["kimi"] = dict(models["kimi"], temperature=0.15)
|
||||
with mock.patch.dict(os.environ, {"MOONSHOT_API_KEY": "sk-moon"}):
|
||||
c = create_llm_client(_cfg(models=models), model="kimi")
|
||||
assert c.default_temperature == 0.15
|
||||
|
||||
def test_l3_no_temperature_keeps_none(self):
|
||||
"""档案未配置 temperature → default_temperature=None（旧硬编码默认）"""
|
||||
with mock.patch.dict(os.environ, {"MOONSHOT_API_KEY": "sk-moon"}):
|
||||
c = create_llm_client(_cfg(), model="kimi")
|
||||
assert c.default_temperature is None
|
||||
|
||||
def test_l3_chat_completion_resolves_default(self):
|
||||
"""chat_completion(temperature=None) → 档案温度；显式传参仍优先"""
|
||||
from llm_client import DeepSeekClient
|
||||
c = DeepSeekClient(api_key="k", model="m", base_url="https://x",
|
||||
default_temperature=0.15)
|
||||
captured = {}
|
||||
with mock.patch("llm_client.requests.post",
|
||||
return_value=mock.MagicMock(
|
||||
status_code=200,
|
||||
json=lambda: {"choices": [{"message": {"content": "ok"}}]})) as mp:
|
||||
c.chat_completion([{"role": "user", "content": "hi"}])
|
||||
captured["default"] = mp.call_args.kwargs["json"]["temperature"]
|
||||
c.chat_completion([{"role": "user", "content": "hi"}], temperature=0.9)
|
||||
captured["explicit"] = mp.call_args.kwargs["json"]["temperature"]
|
||||
assert captured["default"] == 0.15
|
||||
assert captured["explicit"] == 0.9
|
||||
|
||||
def test_l3_chat_completion_hardcoded_default(self):
|
||||
"""无档案温度 + 未传参 → 0.3（与旧版行为一致）"""
|
||||
from llm_client import DeepSeekClient
|
||||
c = DeepSeekClient(api_key="k", model="m", base_url="https://x")
|
||||
with mock.patch("llm_client.requests.post",
|
||||
return_value=mock.MagicMock(
|
||||
status_code=200,
|
||||
json=lambda: {"choices": [{"message": {"content": "ok"}}]})) as mp:
|
||||
c.chat_completion([{"role": "user", "content": "hi"}])
|
||||
assert mp.call_args.kwargs["json"]["temperature"] == 0.3
|
||||
|
||||
# ---------- L5：思考流字段别名 ----------
|
||||
|
||||
def test_l5_reasoning_field_aliases(self):
|
||||
"""reasoning/thinking/thinking_content 字段均归一化为 reasoning 事件"""
|
||||
from llm_client import DeepSeekClient
|
||||
c = DeepSeekClient(api_key="k", model="m", base_url="https://x")
|
||||
cases = [
|
||||
{"reasoning_content": "a"},
|
||||
{"reasoning": "b"},
|
||||
{"thinking": "c"},
|
||||
{"thinking_content": "d"},
|
||||
]
|
||||
for delta in cases:
|
||||
events = list(c._parse_delta(delta, reasoning_enabled=True))
|
||||
assert events == [{"type": "reasoning",
|
||||
"text": list(delta.values())[0]}], delta
|
||||
|
||||
def test_l5_first_present_field_wins(self):
|
||||
"""多字段并存 → 首个命中别名生效，不重复产出"""
|
||||
from llm_client import DeepSeekClient
|
||||
c = DeepSeekClient(api_key="k", model="m", base_url="https://x")
|
||||
events = list(c._parse_delta(
|
||||
{"reasoning_content": "x", "reasoning": "y"}, reasoning_enabled=True))
|
||||
assert events == [{"type": "reasoning", "text": "x"}]
|
||||
|
||||
def test_l5_reasoning_disabled_ignores_all(self):
|
||||
"""reasoning_enabled=False → 别名字段一律不产出（正文不受影响）"""
|
||||
from llm_client import DeepSeekClient
|
||||
c = DeepSeekClient(api_key="k", model="m", base_url="https://x")
|
||||
events = list(c._parse_delta(
|
||||
{"reasoning_content": "x", "content": "hello"}, reasoning_enabled=False))
|
||||
assert events == [{"type": "content", "text": "hello"}]
|
||||
|
||||
|
||||
# ==================== DeepSeekChat 档案级 reasoning 读取 ====================
|
||||
|
||||
class TestChatReasoningFlag:
|
||||
|
||||
Reference in new issue
Block a user