m1saka
fa9640d919
build / build (push) Successful in 2m34s
- New internal/stats (types) and internal/store (SQLite owner: requests + credentials tables, WAL); store implements stats.Recorder. - Stream (SSE tee) and non-stream chat paths parse upstream usage incl. cached_tokens and record per-request; add /api/stats, /api/stats/reset, /admin/stats HTML with cache hit rate. - Drop credentials.json: remove auth file I/O and ZHANLU_CREDENTIALS_FILE; credential precedence is env vars > db row.
79 lines
2.5 KiB
Go
79 lines
2.5 KiB
Go
package stats
|
|
|
|
import (
|
|
"encoding/json"
|
|
"time"
|
|
)
|
|
|
|
// Usage is the subset of the OpenAI chat-completion usage object the recorder
|
|
// persists. Numbers arrive from JSON unmarshal as float64.
|
|
type Usage struct {
|
|
PromptTokens int `json:"prompt_tokens"`
|
|
CompletionTokens int `json:"completion_tokens"`
|
|
TotalTokens int `json:"total_tokens"`
|
|
ReasoningTokens int `json:"reasoning_tokens"`
|
|
CachedTokens int `json:"cached_tokens"`
|
|
|
|
// PromptTokensDetails.CachedTokens is emitted by providers that support
|
|
// prompt caching (OpenAI/DeepSeek/Zhipu litellm gateways). Some upstreams
|
|
// put cached_tokens at the top level instead.
|
|
PromptTokensDetails struct {
|
|
CachedTokens int `json:"cached_tokens"`
|
|
} `json:"prompt_tokens_details"`
|
|
|
|
// CompletionTokensDetails.ReasoningTokens is emitted by reasoning models;
|
|
// some upstreams put reasoning_tokens at top level instead.
|
|
CompletionTokensDetails struct {
|
|
ReasoningTokens int `json:"reasoning_tokens"`
|
|
} `json:"completion_tokens_details"`
|
|
}
|
|
|
|
// ExtractUsage decodes a raw usage value (as produced by encoding/json into an
|
|
// any) into token counts. It accepts both full usage maps and raw JSON bytes.
|
|
// Missing fields default to 0; a nil v yields zero usage.
|
|
func ExtractUsage(v any) Usage {
|
|
var u Usage
|
|
if v == nil {
|
|
return u
|
|
}
|
|
switch t := v.(type) {
|
|
case []byte:
|
|
_ = json.Unmarshal(t, &u)
|
|
case json.RawMessage:
|
|
_ = json.Unmarshal(t, &u)
|
|
case map[string]any:
|
|
// Re-marshal + unmarshal is the simplest robust path for nested
|
|
// *_tokens_details; usage payloads are tiny.
|
|
if b, err := json.Marshal(t); err == nil {
|
|
_ = json.Unmarshal(b, &u)
|
|
}
|
|
}
|
|
if u.ReasoningTokens == 0 {
|
|
u.ReasoningTokens = u.CompletionTokensDetails.ReasoningTokens
|
|
}
|
|
if u.CachedTokens == 0 {
|
|
u.CachedTokens = u.PromptTokensDetails.CachedTokens
|
|
}
|
|
return u
|
|
}
|
|
|
|
// RecordFromUsage builds a Record from a captured usage value plus context.
|
|
func RecordFromUsage(model string, stream bool, usage any, status string, start time.Time) Record {
|
|
u := ExtractUsage(usage)
|
|
if u.TotalTokens == 0 && (u.PromptTokens != 0 || u.CompletionTokens != 0) {
|
|
u.TotalTokens = u.PromptTokens + u.CompletionTokens
|
|
}
|
|
return Record{
|
|
Ts: time.Now(),
|
|
Model: model,
|
|
Stream: stream,
|
|
PromptTokens: u.PromptTokens,
|
|
CompletionTokens: u.CompletionTokens,
|
|
TotalTokens: u.TotalTokens,
|
|
ReasoningTokens: u.ReasoningTokens,
|
|
CachedTokens: u.CachedTokens,
|
|
Status: status,
|
|
LatencyMs: time.Since(start).Milliseconds(),
|
|
}
|
|
}
|