eric/scriptorium
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Serialize cache-controlled chat messages

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-02 23:05:56 +00:00
parent c95d6fcfec
commit efe346893c
3 changed files with 212 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
internal/llm/openai_compatible_client.go
View File

@@ -151,6 +151,8 @@ func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.Genera
PromptTokens: wireResp.Usage.PromptTokens,
CompletionTokens: wireResp.Usage.CompletionTokens,
TotalTokens: wireResp.Usage.TotalTokens,
CachedTokens: wireResp.Usage.PromptTokensDetails.CachedTokens,
CacheWriteTokens: wireResp.Usage.CacheWriteTokens,
},
}, nil
}
@@ -168,12 +170,9 @@ func openAIChatRequestFromGenerateRequest(req domain.GenerateRequest, defaultMod
Model: model,
}
wireReq.Messages = make([]openAIChatMessage, 0, len(req.Prompt.Messages))
wireReq.Messages = make([]openAIChatRequestMessage, 0, len(req.Prompt.Messages))
for _, msg := range req.Prompt.Messages {
wireReq.Messages = append(wireReq.Messages, openAIChatMessage{
Role: msg.Role,
Content: msg.Content,
})
wireReq.Messages = append(wireReq.Messages, openAIChatRequestMessageFromRenderedMessage(msg))
}
if req.Target.Temperature != 0 {
@@ -200,28 +199,48 @@ func openAIChatRequestFromGenerateRequest(req domain.GenerateRequest, defaultMod
}
type openAIChatRequest struct {
Model string `json:"model"`
Messages []openAIChatMessage `json:"messages"`
Temperature *float64 `json:"temperature,omitempty"`
MaxTokens *int `json:"max_tokens,omitempty"`
TopP *float64 `json:"top_p,omitempty"`
ServiceTier string `json:"service_tier,omitempty"`
ResponseFormat *openAIResponseFormat `json:"response_format,omitempty"`
Model string `json:"model"`
Messages []openAIChatRequestMessage `json:"messages"`
Temperature *float64 `json:"temperature,omitempty"`
MaxTokens *int `json:"max_tokens,omitempty"`
TopP *float64 `json:"top_p,omitempty"`
ServiceTier string `json:"service_tier,omitempty"`
ResponseFormat *openAIResponseFormat `json:"response_format,omitempty"`
}
type openAIChatMessage struct {
type openAIChatRequestMessage struct {
Role string `json:"role"`
Content any `json:"content"`
}
type openAIChatTextContentBlock struct {
Type string `json:"type"`
Text string `json:"text"`
CacheControl *openAICacheControl `json:"cache_control,omitempty"`
}
type openAICacheControl struct {
Type string `json:"type"`
TTL string `json:"ttl,omitempty"`
}
type openAIChatResponseMessage struct {
Role string `json:"role"`
Content string `json:"content"`
}
type openAIChatResponse struct {
Choices []struct {
Message openAIChatMessage `json:"message"`
Message openAIChatResponseMessage `json:"message"`
} `json:"choices"`
Usage struct {
PromptTokens int `json:"prompt_tokens"`
CompletionTokens int `json:"completion_tokens"`
TotalTokens int `json:"total_tokens"`
PromptTokens int `json:"prompt_tokens"`
CompletionTokens int `json:"completion_tokens"`
TotalTokens int `json:"total_tokens"`
PromptTokensDetails struct {
CachedTokens int `json:"cached_tokens"`
} `json:"prompt_tokens_details"`
CacheWriteTokens int `json:"cache_write_tokens"`
} `json:"usage"`
}
@@ -236,6 +255,28 @@ type openAIJSONSchemaEnvelope struct {
Schema any `json:"schema"`
}
func openAIChatRequestMessageFromRenderedMessage(msg domain.RenderedMessage) openAIChatRequestMessage {
wireMsg := openAIChatRequestMessage{
Role: msg.Role,
Content: msg.Content,
}
if msg.CacheControl == nil {
return wireMsg
}
wireMsg.Content = []openAIChatTextContentBlock{
{
Type: "text",
Text: msg.Content,
CacheControl: &openAICacheControl{
Type: string(msg.CacheControl.Type),
TTL: msg.CacheControl.TTL,
},
},
}
return wireMsg
}
func toOpenAIResponseFormat(spec *domain.StructuredOutputSpec) (*openAIResponseFormat, error) {
if spec == nil {
return nil, nil