Files
new-api/relay/common/tool_usage_test.go
T
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
2026-07-27 15:56:21 +08:00

349 lines
9.8 KiB
Go

package common
import (
"strings"
"testing"
"github.com/QuantumNous/new-api/relaykit/dto"
"github.com/QuantumNous/new-api/setting/operation_setting"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestCountBillableToolCallWebSearchPrefersDeclaredWebSearch(t *testing.T) {
info := &RelayInfo{
OriginModelName: "gpt-5.1",
ResponsesUsageInfo: &ResponsesUsageInfo{
BuiltInTools: map[string]*BuildInToolInfo{
dto.BuildInToolWebSearch: {ToolName: dto.BuildInToolWebSearch, CallCount: 0},
},
},
}
info.CountBillableToolCall(dto.BuildInCallWebSearchCall, "")
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearch)
assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearch].CallCount)
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearchPreview)
}
func TestCountBillableToolCallWebSearchDefaultsToPreview(t *testing.T) {
info := &RelayInfo{OriginModelName: "gpt-5.1"}
info.CountBillableToolCall(dto.BuildInCallWebSearchCall, "")
require.NotNil(t, info.ResponsesUsageInfo)
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearchPreview)
assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview].CallCount)
}
func TestCountBillableToolCallFunctionCallRequiresPrice(t *testing.T) {
operation_setting.SetToolPriceForTest("my_priced_fn", 5.0)
t.Cleanup(func() {
operation_setting.DeleteToolPriceForTest("my_priced_fn")
})
info := &RelayInfo{OriginModelName: "gpt-5.1"}
info.CountBillableToolCall(dto.BuildInCallFunctionCall, "my_priced_fn")
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, "my_priced_fn")
assert.Equal(t, 1, info.ResponsesUsageInfo.BuiltInTools["my_priced_fn"].CallCount)
info.CountBillableToolCall(dto.BuildInCallFunctionCall, "unpriced_fn")
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, "unpriced_fn")
}
func TestCountBillableToolCallFunctionCallSkipsReservedNames(t *testing.T) {
info := &RelayInfo{OriginModelName: "gpt-5.1"}
info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolWebSearchPreview)
info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolFileSearch)
info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolGoogleSearch)
info.CountBillableToolCall(dto.BuildInCallFunctionCall, dto.BuildInToolImageGeneration)
if info.ResponsesUsageInfo != nil {
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolWebSearchPreview)
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolFileSearch)
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolGoogleSearch)
assert.NotContains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolImageGeneration)
}
}
func TestImageGenerationCallCounterCompletedOutputs(t *testing.T) {
t.Parallel()
tests := []struct {
name string
observe func(c *ImageGenerationCallCounter)
wantCount int
}{
{
name: "one final result",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "completed",
Result: "base64-a",
}, &idx)
},
wantCount: 1,
},
{
name: "two distinct finals",
observe: func(c *ImageGenerationCallCounter) {
idx0, idx1 := 0, 1
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Result: "base64-a",
}, &idx0)
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_2",
Result: "base64-b",
}, &idx1)
},
wantCount: 2,
},
{
name: "empty result",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Result: " ",
}, &idx)
},
wantCount: 0,
},
{
name: "failed status",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "failed",
Result: "base64-a",
}, &idx)
},
wantCount: 0,
},
{
name: "incomplete status",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "incomplete",
Result: "base64-a",
}, &idx)
},
wantCount: 0,
},
{
name: "cancelled status",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "cancelled",
Result: "base64-a",
}, &idx)
},
wantCount: 0,
},
{
name: "canceled status",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "canceled",
Result: "base64-a",
}, &idx)
},
wantCount: 0,
},
{
name: "partial status",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "partial",
Result: "partial-bytes",
}, &idx)
},
wantCount: 0,
},
{
name: "id dedup",
observe: func(c *ImageGenerationCallCounter) {
idx0, idx1 := 0, 1
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
CallId: "call_a",
Result: "base64-a",
}, &idx0)
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
CallId: "call_b",
Result: "base64-b",
}, &idx1)
},
wantCount: 1,
},
{
name: "index dedup",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Result: "base64-a",
}, &idx)
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_2",
Result: "base64-b",
}, &idx)
},
wantCount: 1,
},
{
name: "result hash dedup",
observe: func(c *ImageGenerationCallCounter) {
idx0, idx1 := 0, 1
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
Result: "same-bytes",
}, &idx0)
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
Result: "same-bytes",
}, &idx1)
},
wantCount: 1,
},
{
name: "output_item.done plus completed dedup",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
item := &dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
CallId: "call_1",
Status: "completed",
Result: "base64-a",
}
c.Observe(item, &idx)
c.Observe(item, &idx)
},
wantCount: 1,
},
{
name: "output_item.done plus incomplete equals zero",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "completed",
Result: "base64-a",
}, &idx)
c.Reset()
},
wantCount: 0,
},
{
name: "partial event equals zero",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: "image_generation_call.partial_image",
ID: "img_1",
Result: "partial-bytes",
}, &idx)
},
wantCount: 0,
},
{
name: "in_progress with final result counts",
observe: func(c *ImageGenerationCallCounter) {
idx := 0
c.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_1",
Status: "in_progress",
Result: "base64-a",
}, &idx)
},
wantCount: 1,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
counter := &ImageGenerationCallCounter{}
tt.observe(counter)
assert.Equal(t, tt.wantCount, counter.Count())
})
}
}
func TestImageGenerationCallCounterCommitCapsAtMaxImageN(t *testing.T) {
t.Parallel()
counter := &ImageGenerationCallCounter{}
for i := 0; i < dto.MaxImageN+3; i++ {
idx := i
counter.Observe(&dto.ResponsesOutput{
Type: dto.ResponsesOutputTypeImageGenerationCall,
ID: "img_" + strings.Repeat("a", i+1),
Result: "result-" + strings.Repeat("b", i+1),
}, &idx)
}
require.Equal(t, dto.MaxImageN+3, counter.Count())
info := &RelayInfo{}
counter.Commit(info)
require.Contains(t, info.ResponsesUsageInfo.BuiltInTools, dto.BuildInToolImageGeneration)
assert.Equal(t, dto.MaxImageN, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
}
func TestImageGenerationCallCounterCommitDoesNotBillDeclarationsAlone(t *testing.T) {
t.Parallel()
info := &RelayInfo{
ResponsesUsageInfo: &ResponsesUsageInfo{
BuiltInTools: map[string]*BuildInToolInfo{
dto.BuildInToolImageGeneration: {
ToolName: dto.BuildInToolImageGeneration,
CallCount: 0,
},
},
},
}
(&ImageGenerationCallCounter{}).Commit(info)
assert.Equal(t, 0, info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration].CallCount)
}
func TestIsNonBillableResponsesStatus(t *testing.T) {
t.Parallel()
assert.True(t, IsNonBillableResponsesStatus([]byte(`"failed"`)))
assert.True(t, IsNonBillableResponsesStatus([]byte(`"incomplete"`)))
assert.True(t, IsNonBillableResponsesStatus([]byte(`"cancelled"`)))
assert.True(t, IsNonBillableResponsesStatus([]byte(`"canceled"`)))
assert.False(t, IsNonBillableResponsesStatus([]byte(`"completed"`)))
assert.False(t, IsNonBillableResponsesStatus(nil))
}