mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-13 14:10:59 +00:00
refactor(provider): use LiteLLM as unified LLM requester backend (#2150)
* refactor(provider): use LiteLLM as unified LLM requester backend
- Replace 23+ individual requester implementations with unified litellmchat.py
- Add litellm_provider field to 27 YAML manifests for provider routing
- Delete redundant requester subclasses
- Add unit tests for LiteLLMRequester (29 tests)
- Fix num_retries parameter name (was max_retries)
- Fix exception handling order for subclass exceptions
LiteLLM provides unified API for 100+ providers, eliminating need for
provider-specific requesters.
* fix: ruff format provider.py
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* refactor(provider): simplify LiteLLM requester usage handling
- Remove unused Anthropic-specific tool schema generation
- Share completion argument construction between normal and streaming calls
- Use LiteLLM/OpenAI native usage fields for monitoring
- Collect stream token usage from LiteLLM stream_options
- Update LiteLLM requester tests for unified usage fields
* restore: restore deleted provider requester files
Restore individual provider requester implementations that were
removed in de61b5d3. These files coexist with the unified
litellmchat.py backend.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat: update requesters and improve provider selection UI
- Added `litellm_provider` field to various requesters' YAML configurations.
- Removed obsolete Python requester files for OpenRouter, PPIO, QHAIGC, ShengSuanYun, SiliconFlow, Space, TokenPony, VolcArk, and Xai.
- Introduced new requesters for Tencent and Together AI with corresponding YAML configurations and SVG icons.
- Enhanced the ProviderForm component to include a searchable dropdown for selecting providers, improving user experience.
- Updated localization files to include search provider text for both English and Chinese.
* fix(provider): align litellm rebase with master
* fix(provider): capture streaming token usage; add token observability
The LiteLLM streaming requester only captured usage when a chunk had an
empty `choices` list. Many OpenAI-compatible gateways (e.g. new-api) and
providers send the final usage payload in a chunk that still carries an
empty-delta choice, so streamed calls always recorded 0 tokens in the
monitoring logs/dashboard (non-streaming worked).
- Capture stream usage whenever a chunk carries it, regardless of choices
- Add robust _normalize_usage (dict/obj shapes, derive missing total_tokens)
- Register litellm in bootutils/deps.py (was in pyproject only)
- Add MonitoringService.get_token_statistics + /monitoring/token-statistics
endpoint: summary, per-model breakdown, token timeseries, and a
zero-token-success data-quality signal
- Add TokenMonitoring dashboard tab (summary tiles, stacked token chart,
per-model table) + i18n (en/zh)
- Regression tests for stream usage capture and usage normalization
Verified end-to-end against a real OpenAI-compatible endpoint with
gpt-5.5 and claude-opus-4-8: tokens now recorded non-zero for both
streaming and non-streaming paths.
* refactor(provider): simplify litellm capabilities
* style: simplify wrapped expressions
* feat(models): persist context metadata
* fix(provider): handle dict embeddings and openai-compatible rerank in LiteLLMRequester
- invoke_embedding: support both object- and dict-shaped response.data
entries (OpenAI-compatible gateways like new-api return dicts)
- invoke_rerank: litellm.arerank rejects the 'openai' provider, so for
openai-compatible (or unspecified) providers call the standard
Jina/Cohere-style POST /v1/rerank endpoint directly over HTTP
- accept both 'relevance_score' and 'score' fields in rerank results
- add unit tests for the openai-compatible HTTP rerank path
* feat(provider): enforce requester support_type when adding models
- frontend: AddModelPopover only shows model-type tabs (llm/embedding/
rerank) that the provider's requester declares in its manifest
support_type; ModelsDialog fetches requester manifests and maps
requester -> support_type, passed down through ProviderCard
- backend: add _validate_provider_supports guard in create_llm_model /
create_embedding_model / create_rerank_model so a model cannot be
attached to a provider whose requester does not support that type,
even if the frontend restriction is bypassed (manifests without
support_type are allowed for backward compatibility)
- manifests: correct support_type for providers that do not offer all
three model types:
- llm only: anthropic, deepseek, groq, moonshot, openrouter, xai
- llm + text-embedding: openai, gemini, mistral
- add rerank to new-api (verified working via /v1/rerank)
- set llm + text-embedding + rerank for aggregator/unknown gateways
* feat(provider): add searchable alias to requester manifests
- add a free-text 'alias' field to every requester manifest spec,
containing the vendor's English/Chinese names, pinyin, common
nicknames and flagship model-series names (e.g. moonshot -> kimi,
月之暗面; zhipu -> glm, 智谱清言)
- frontend: ProviderForm requester search now also matches against
alias (substring/contains), so searching 'kimi' surfaces Moonshot,
'硅基' surfaces SiliconFlow, etc.
- also fix support_type: openrouter (relay) supports embedding+rerank;
LangBot Space gains rerank (coming soon)
* fix(provider): make support_type guard defensive against incomplete model_mgr
- _validate_provider_supports now uses getattr to gracefully skip when
model_mgr / provider_dict / manifest lookup is unavailable, instead of
raising AttributeError (fixes unit tests that mock ap.model_mgr as a
bare SimpleNamespace)
- add TestValidateProviderSupports covering: allow supported type,
reject unsupported type, allow when support_type missing, allow when
provider unknown, degrade safely when model_mgr is incomplete
* fix(persistence): guard 0004 migration against missing llm_models table
The 0004_add_llm_model_context_length migration called
inspector.get_columns('llm_models') unconditionally, raising
NoSuchTableError when the table does not exist (e.g. migrating a
fresh/empty DB, as exercised by the integration tests where
create_all() registers no tables because the ORM models are not
imported). Every other migration guards with a table-existence check
first; add the same guard here for both upgrade and downgrade.
Also restore the test head assertion to 0004 (it had been lowered to
0003 to mask this failure).
* Merge branch 'master' into feat/litellm
Resolve conflicts:
- uv.lock: regenerated via 'uv lock' to reconcile litellm/fastuuid
(ours) with openai bump (master).
- Alembic migrations: master added 0004_add_mcp_readme while this
branch added 0004_add_llm_model_context_length, both as children of
0003 (would create multiple heads). Re-chain the litellm migration as
0005_add_llm_model_context_length with down_revision=0004_add_mcp_readme
for a single linear head. Update test head assertion accordingly.
* fix(persistence): shorten migration revision id to fit varchar(32)
PostgreSQL stores alembic_version.version_num as varchar(32).
'0005_add_llm_model_context_length' (33 chars) overflowed it, raising
StringDataRightTruncationError in the PG migration tests. Rename the
revision (and file) to '0005_add_llm_context_length' (27 chars) and
update the head assertions in both SQLite and PostgreSQL migration
tests.
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: fdc310 <2213070223@qq.com>
Co-authored-by: RockChinQ <rockchinq@gmail.com>
This commit is contained in:
huanghuoguoguo
@@ -1,264 +0,0 @@
|
||||
"""Tests for OllamaChatCompletions requester.
|
||||
|
||||
Tests model inference, payload construction, and error handling.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
from unittest.mock import AsyncMock, MagicMock
|
||||
import pytest
|
||||
|
||||
from langbot.pkg.provider.modelmgr.errors import RequesterError
|
||||
|
||||
|
||||
class TestOllamaRequesterConfig:
|
||||
"""Tests for default config."""
|
||||
|
||||
def test_default_config_values(self):
|
||||
"""Check default_config."""
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
assert OllamaChatCompletions.default_config['base_url'] == 'http://127.0.0.1:11434'
|
||||
assert OllamaChatCompletions.default_config['timeout'] == 120
|
||||
|
||||
def test_config_override(self):
|
||||
"""Config can override defaults."""
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
mock_app = MagicMock()
|
||||
req = OllamaChatCompletions(mock_app, {
|
||||
'base_url': 'http://custom.ollama:11434',
|
||||
'timeout': 300,
|
||||
})
|
||||
|
||||
assert req.requester_cfg['base_url'] == 'http://custom.ollama:11434'
|
||||
assert req.requester_cfg['timeout'] == 300
|
||||
|
||||
|
||||
class TestOllamaInferModelType:
|
||||
"""Tests for _infer_model_type pure function."""
|
||||
|
||||
@pytest.fixture
|
||||
def requester(self):
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
return OllamaChatCompletions(MagicMock(), {})
|
||||
|
||||
def test_infer_embedding_from_name(self, requester):
|
||||
"""Embedding keywords return 'embedding'."""
|
||||
assert requester._infer_model_type('nomic-embed-text') == 'embedding'
|
||||
assert requester._infer_model_type('bge-large') == 'embedding'
|
||||
assert requester._infer_model_type('text-embedding') == 'embedding'
|
||||
|
||||
def test_infer_llm_from_name(self, requester):
|
||||
"""Non-embedding keywords return 'llm'."""
|
||||
assert requester._infer_model_type('llama2') == 'llm'
|
||||
assert requester._infer_model_type('mistral') == 'llm'
|
||||
assert requester._infer_model_type('codellama') == 'llm'
|
||||
|
||||
def test_infer_model_type_none(self, requester):
|
||||
"""None model_id returns 'llm'."""
|
||||
assert requester._infer_model_type(None) == 'llm'
|
||||
|
||||
def test_infer_model_type_empty(self, requester):
|
||||
"""Empty model_id returns 'llm'."""
|
||||
assert requester._infer_model_type('') == 'llm'
|
||||
|
||||
|
||||
class TestOllamaInferModelAbilities:
|
||||
"""Tests for _infer_model_abilities pure function."""
|
||||
|
||||
@pytest.fixture
|
||||
def requester(self):
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
return OllamaChatCompletions(MagicMock(), {})
|
||||
|
||||
def test_infer_vision_ability(self, requester):
|
||||
"""Vision keywords add 'vision' ability."""
|
||||
item = {
|
||||
'details': {
|
||||
'family': 'llava',
|
||||
}
|
||||
}
|
||||
|
||||
abilities = requester._infer_model_abilities(item, 'llava-v1.5')
|
||||
assert 'vision' in abilities
|
||||
|
||||
def test_infer_vision_from_model_id(self, requester):
|
||||
"""Vision keywords in model_id add 'vision' ability."""
|
||||
item = {}
|
||||
abilities = requester._infer_model_abilities(item, 'llava-7b')
|
||||
assert 'vision' in abilities
|
||||
|
||||
def test_infer_func_call_ability(self, requester):
|
||||
"""Tool/function keywords add 'func_call' ability."""
|
||||
item = {
|
||||
'details': {
|
||||
'families': ['tools'],
|
||||
}
|
||||
}
|
||||
|
||||
abilities = requester._infer_model_abilities(item, 'model')
|
||||
assert 'func_call' in abilities
|
||||
|
||||
def test_infer_no_abilities(self, requester):
|
||||
"""No matching keywords returns empty abilities."""
|
||||
item = {
|
||||
'details': {
|
||||
'family': 'llama',
|
||||
}
|
||||
}
|
||||
|
||||
abilities = requester._infer_model_abilities(item, 'llama-2')
|
||||
assert len(abilities) == 0
|
||||
|
||||
def test_infer_multiple_abilities(self, requester):
|
||||
"""Multiple keywords can add multiple abilities."""
|
||||
item = {
|
||||
'details': {
|
||||
'family': 'vision',
|
||||
'families': ['tools'],
|
||||
}
|
||||
}
|
||||
|
||||
abilities = requester._infer_model_abilities(item, 'vision-tool-model')
|
||||
assert 'vision' in abilities
|
||||
assert 'func_call' in abilities
|
||||
|
||||
|
||||
class TestOllamaMakeMessage:
|
||||
"""Tests for _make_msg response parsing."""
|
||||
|
||||
@pytest.fixture
|
||||
def requester(self):
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
return OllamaChatCompletions(MagicMock(), {})
|
||||
|
||||
def _create_ollama_response(self, content, tool_calls=None):
|
||||
"""Helper to create mock ollama response."""
|
||||
import ollama
|
||||
|
||||
mock_response = MagicMock(spec=ollama.ChatResponse)
|
||||
mock_message = MagicMock(spec=ollama.Message)
|
||||
mock_message.content = content
|
||||
mock_message.tool_calls = tool_calls
|
||||
mock_response.message = mock_message
|
||||
|
||||
return mock_response
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_make_msg_text_content(self, requester):
|
||||
"""Text content is extracted."""
|
||||
mock_response = self._create_ollama_response('Hello world')
|
||||
|
||||
result = await requester._make_msg(mock_response)
|
||||
|
||||
assert result.content == 'Hello world'
|
||||
assert result.role == 'assistant'
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_make_msg_with_tool_calls(self, requester):
|
||||
"""Tool calls are parsed."""
|
||||
mock_tool_call = MagicMock()
|
||||
mock_tool_call.function = MagicMock()
|
||||
mock_tool_call.function.name = 'get_weather'
|
||||
mock_tool_call.function.arguments = {'location': 'Beijing'}
|
||||
|
||||
mock_response = self._create_ollama_response('', tool_calls=[mock_tool_call])
|
||||
|
||||
result = await requester._make_msg(mock_response)
|
||||
|
||||
assert result.tool_calls is not None
|
||||
assert len(result.tool_calls) == 1
|
||||
assert result.tool_calls[0].function.name == 'get_weather'
|
||||
# Arguments should be JSON string
|
||||
assert isinstance(result.tool_calls[0].function.arguments, str)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_make_msg_empty_message_raises(self, requester):
|
||||
"""Empty message raises ValueError."""
|
||||
mock_response = MagicMock()
|
||||
mock_response.message = None
|
||||
|
||||
with pytest.raises(ValueError, match='message'):
|
||||
await requester._make_msg(mock_response)
|
||||
|
||||
|
||||
class TestOllamaErrorHandling:
|
||||
"""Tests for error handling branches."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_app(self):
|
||||
app = MagicMock()
|
||||
app.tool_mgr = MagicMock()
|
||||
app.tool_mgr.generate_tools_for_openai = AsyncMock(return_value=[])
|
||||
return app
|
||||
|
||||
@pytest.fixture
|
||||
def requester_with_mocked_client(self, mock_app):
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
req = OllamaChatCompletions(mock_app, {})
|
||||
req.client = MagicMock()
|
||||
req.client.chat = AsyncMock()
|
||||
|
||||
return req
|
||||
|
||||
@pytest.fixture
|
||||
def mock_model(self):
|
||||
model = MagicMock()
|
||||
model.model_entity = MagicMock()
|
||||
model.model_entity.name = 'llama2'
|
||||
model.provider = MagicMock()
|
||||
model.provider.token_mgr = MagicMock()
|
||||
model.provider.token_mgr.get_token = MagicMock(return_value='')
|
||||
return model
|
||||
|
||||
@pytest.fixture
|
||||
def mock_message(self):
|
||||
msg = MagicMock()
|
||||
msg.role = 'user'
|
||||
msg.content = 'test'
|
||||
msg.dict = MagicMock(return_value={'role': 'user', 'content': 'test'})
|
||||
return msg
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_timeout_error(self, requester_with_mocked_client, mock_model, mock_message):
|
||||
"""TimeoutError is converted to RequesterError."""
|
||||
requester_with_mocked_client.client.chat = AsyncMock(side_effect=asyncio.TimeoutError())
|
||||
|
||||
with pytest.raises(RequesterError) as exc:
|
||||
await requester_with_mocked_client.invoke_llm(
|
||||
query=None,
|
||||
model=mock_model,
|
||||
messages=[mock_message],
|
||||
)
|
||||
|
||||
assert '超时' in str(exc.value)
|
||||
|
||||
|
||||
class TestOllamaScanModels:
|
||||
"""Tests for scan_models method."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_app(self):
|
||||
return MagicMock()
|
||||
|
||||
@pytest.fixture
|
||||
def requester(self, mock_app):
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import OllamaChatCompletions
|
||||
|
||||
req = OllamaChatCompletions(mock_app, {
|
||||
'base_url': 'http://127.0.0.1:11434',
|
||||
'timeout': 120,
|
||||
})
|
||||
return req
|
||||
|
||||
def test_requester_name_constant(self):
|
||||
"""REQUESTER_NAME constant exists."""
|
||||
from langbot.pkg.provider.modelmgr.requesters.ollamachat import REQUESTER_NAME
|
||||
|
||||
assert REQUESTER_NAME == 'ollama-chat'
|
||||
Reference in New Issue
Block a user