Calcium-Ion
86ac0f7745
* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
97 lines
2.6 KiB
Go
97 lines
2.6 KiB
Go
package ollama
|
|
|
|
import (
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestOllamaChatHandlerNonStreamToolCalls(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
|
|
tests := []struct {
|
|
name string
|
|
raw string
|
|
}{
|
|
{
|
|
name: "compact json per-line parse path",
|
|
raw: `{"model":"llama3.1","created_at":"2026-05-27T12:00:00Z","message":{"role":"assistant","content":"","tool_calls":[{"function":{"name":"get_weather","arguments":{"city":"Paris","days":0}}}]},"done":true,"done_reason":"stop","prompt_eval_count":5,"eval_count":7}`,
|
|
},
|
|
{
|
|
name: "pretty json fallback parse path",
|
|
raw: `{
|
|
"model": "llama3.1",
|
|
"created_at": "2026-05-27T12:00:00Z",
|
|
"message": {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{
|
|
"function": {
|
|
"name": "get_weather",
|
|
"arguments": {
|
|
"city": "Paris",
|
|
"days": 0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"prompt_eval_count": 5,
|
|
"eval_count": 7
|
|
}`,
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
w := httptest.NewRecorder()
|
|
c, _ := gin.CreateTestContext(w)
|
|
|
|
resp := &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Header: make(http.Header),
|
|
Body: io.NopCloser(strings.NewReader(tt.raw)),
|
|
}
|
|
|
|
usage, apiErr := ollamaChatHandler(c, &relaycommon.RelayInfo{
|
|
ChannelMeta: &relaycommon.ChannelMeta{UpstreamModelName: "fallback-model"},
|
|
}, resp)
|
|
require.Nil(t, apiErr)
|
|
require.NotNil(t, usage)
|
|
assert.Equal(t, 12, usage.TotalTokens)
|
|
|
|
var out dto.OpenAITextResponse
|
|
require.NoError(t, common.Unmarshal(w.Body.Bytes(), &out))
|
|
require.Len(t, out.Choices, 1)
|
|
assert.Equal(t, constant.FinishReasonToolCalls, out.Choices[0].FinishReason)
|
|
|
|
var toolCalls []dto.ToolCallResponse
|
|
require.NoError(t, common.Unmarshal(out.Choices[0].Message.ToolCalls, &toolCalls))
|
|
require.Len(t, toolCalls, 1)
|
|
assert.NotEmpty(t, toolCalls[0].ID)
|
|
assert.Equal(t, "function", toolCalls[0].Type)
|
|
assert.Equal(t, "get_weather", toolCalls[0].Function.Name)
|
|
assert.Nil(t, toolCalls[0].Index)
|
|
|
|
var args map[string]any
|
|
require.NoError(t, common.Unmarshal([]byte(toolCalls[0].Function.Arguments), &args))
|
|
assert.Equal(t, "Paris", args["city"])
|
|
assert.Equal(t, float64(0), args["days"])
|
|
})
|
|
}
|
|
}
|