This commit captures both the prior accumulated work-in-progress
(framework migration web/→svelte/, postgres storage, conversation
viewer, dashboard auth, OpenAPI spec, integration tests) AND today's
operational improvements layered on top. History wasn't checkpointed
incrementally; happy to split it via interactive rebase if a reviewer
wants smaller commits.
Today's changes (in addition to the older WIP):
1. Configurable upstream response-header timeout
- ANTHROPIC_RESPONSE_HEADER_TIMEOUT env (default 300s)
- Replaces hardcoded 300s in provider/anthropic.go that was firing
on opus + 1M-context + extended thinking non-streaming requests
- Files: internal/config/config.go, internal/provider/anthropic.go
2. Structured forward-error diagnostic logging
- When a forward to Anthropic fails, log a single key=value line
with request_id, model, stream, body_bytes, has_thinking,
anthropic_beta, query, elapsed, ctx_err — alongside the existing
human-readable error line for back-compat
- Files: internal/handler/handlers.go (logForwardFailure)
3. Full SSE protocol passthrough + Flusher fix
- handler/handlers.go: forward all SSE lines verbatim (event:, id:,
retry:, : comments, blank-line terminators), not only data:.
Previous code produced malformed SSE for strict parsers.
- middleware/logging.go: explicit Flush() method on responseWriter.
Embedding http.ResponseWriter (interface) does not auto-promote
Flush(), so every w.(http.Flusher) check in the streaming
handler was returning ok=false and SSE writes buffered in net/http
until the body closed.
4. Non-streaming → streaming demotion (feature-flagged)
- ANTHROPIC_DEMOTE_NONSTREAMING env (default false)
- When enabled and the routed provider is anthropic, force stream=true
upstream for clients that asked for stream=false. Receive SSE,
accumulate via accumulateSSEToMessage (handles text, tool_use with
partial_json reassembly, thinking, signature, citations_delta,
usage merge), and synthesize a single non-streaming JSON response.
- Eliminates the ResponseHeaderTimeout class of failure entirely.
- Body rewrite uses json.Decoder + UseNumber() to preserve integer
precision in unknown nested fields (tool inputs from prior turns).
- Files: internal/config/config.go, internal/handler/handlers.go,
cmd/proxy/main.go, cmd/proxy/main_test.go
5. Live operational state: /livez gauge + graceful drain
- New internal/runtime package: atomic in-flight counter + draining flag
- New middleware/inflight.go: increments runtime gauge, applied to
/v1/* subrouter so Messages, ChatCompletions, and ProxyPassthrough
are all counted
- /v1/* moved to a gorilla/mux subrouter so the InFlight middleware
applies surgically; /health, /livez, /openapi.* remain on parent
router (unauthenticated, uncounted)
- Health handler returns 503 draining when runtime.IsDraining() is
true, so Traefik stops routing to a slot before drain begins
- New /livez handler returns {status, in_flight, draining, timestamp}
- SIGTERM handler in main.go: SetDraining(true), poll for in_flight==0
with 32-min ceiling and 1s tick (logs every 10s), then srv.Shutdown
- Auth bypass list extended with /livez
- Files: internal/runtime/runtime.go (new),
internal/middleware/inflight.go (new),
internal/middleware/auth.go,
internal/handler/handlers.go (Health, Livez, runtime import),
cmd/proxy/main.go (subrouter, drain loop)
6. OpenAPI spec updates
- Document Health 503 response and new DrainingResponse schema
- Add /livez path with LivezResponse schema
- Files: internal/handler/openapi.go
Verified: go build ./... clean, go test ./... all pass, go vet clean.
Three rounds of codex peer review across changes 1-5; all feedback
addressed (citations_delta, json.Number precision, drain-loop logging
via lastLog timestamp, PathPrefix tightened to "/v1/").
163 lines
3.8 KiB
Go
163 lines
3.8 KiB
Go
package service
|
|
|
|
import (
|
|
"database/sql"
|
|
"encoding/json"
|
|
|
|
"github.com/seifghazi/claude-code-monitor/internal/model"
|
|
)
|
|
|
|
type responseBodySummary struct {
|
|
Usage *model.AnthropicUsage `json:"usage"`
|
|
StopReason string `json:"stop_reason"`
|
|
}
|
|
|
|
func decodeStoredResponse(responseJSON sql.NullString) (*model.ResponseLog, bool) {
|
|
if !responseJSON.Valid || responseJSON.String == "" {
|
|
return nil, false
|
|
}
|
|
|
|
var resp model.ResponseLog
|
|
if err := json.Unmarshal([]byte(responseJSON.String), &resp); err != nil {
|
|
return nil, false
|
|
}
|
|
|
|
return &resp, true
|
|
}
|
|
|
|
func decodeResponseBodySummary(body json.RawMessage) (*responseBodySummary, bool) {
|
|
if len(body) == 0 {
|
|
return nil, false
|
|
}
|
|
|
|
var summary responseBodySummary
|
|
if err := json.Unmarshal(body, &summary); err != nil {
|
|
return nil, false
|
|
}
|
|
|
|
return &summary, true
|
|
}
|
|
|
|
func totalTokensFromUsage(usage *model.AnthropicUsage) int64 {
|
|
if usage == nil {
|
|
return 0
|
|
}
|
|
|
|
return int64(
|
|
usage.InputTokens +
|
|
usage.OutputTokens +
|
|
usage.CacheReadInputTokens +
|
|
usage.CacheCreationInputTokens)
|
|
}
|
|
|
|
func totalTokensFromStoredResponse(responseJSON sql.NullString) int64 {
|
|
input, output, cache, ok := usageCountsFromStoredResponse(responseJSON)
|
|
if !ok {
|
|
return 0
|
|
}
|
|
|
|
return input + output + cache
|
|
}
|
|
|
|
func responseTimeFromStoredResponse(responseJSON sql.NullString) int64 {
|
|
resp, ok := decodeStoredResponse(responseJSON)
|
|
if !ok {
|
|
return 0
|
|
}
|
|
|
|
return resp.ResponseTime
|
|
}
|
|
|
|
func applyStoredResponseToSummary(summary *model.RequestSummary, responseJSON sql.NullString) {
|
|
resp, ok := decodeStoredResponse(responseJSON)
|
|
if !ok {
|
|
return
|
|
}
|
|
|
|
summary.StatusCode = resp.StatusCode
|
|
summary.ResponseTime = resp.ResponseTime
|
|
|
|
bodySummary, ok := decodeResponseBodySummary(resp.Body)
|
|
if !ok {
|
|
return
|
|
}
|
|
|
|
summary.Usage = bodySummary.Usage
|
|
summary.StopReason = bodySummary.StopReason
|
|
}
|
|
|
|
func usageCountsFromStoredResponse(responseJSON sql.NullString) (input, output, cache int64, ok bool) {
|
|
resp, ok := decodeStoredResponse(responseJSON)
|
|
if !ok {
|
|
return 0, 0, 0, false
|
|
}
|
|
|
|
bodySummary, ok := decodeResponseBodySummary(resp.Body)
|
|
if !ok || bodySummary.Usage == nil {
|
|
return 0, 0, 0, false
|
|
}
|
|
|
|
return int64(bodySummary.Usage.InputTokens),
|
|
int64(bodySummary.Usage.OutputTokens),
|
|
int64(bodySummary.Usage.CacheCreationInputTokens + bodySummary.Usage.CacheReadInputTokens),
|
|
true
|
|
}
|
|
|
|
func addDailyTokens(dailyMap map[string]*model.DailyTokens, date, modelName string, tokens int64) {
|
|
if daily, ok := dailyMap[date]; ok {
|
|
daily.Tokens += tokens
|
|
daily.Requests++
|
|
daily.Models = addDailyModelStat(daily.Models, modelName, tokens)
|
|
return
|
|
}
|
|
|
|
dailyMap[date] = &model.DailyTokens{
|
|
Date: date,
|
|
Tokens: tokens,
|
|
Requests: 1,
|
|
Models: addDailyModelStat(nil, modelName, tokens),
|
|
}
|
|
}
|
|
|
|
func addHourlyTokens(bucketMap map[string]*model.HourlyTokens, bucketKey, bucketLabel, modelName string, tokens int64) {
|
|
if bucket, ok := bucketMap[bucketKey]; ok {
|
|
bucket.Tokens += tokens
|
|
bucket.Requests++
|
|
bucket.Models = addDailyModelStat(bucket.Models, modelName, tokens)
|
|
return
|
|
}
|
|
|
|
bucketMap[bucketKey] = &model.HourlyTokens{
|
|
Hour: 0,
|
|
Label: bucketLabel,
|
|
Tokens: tokens,
|
|
Requests: 1,
|
|
Models: addDailyModelStat(nil, modelName, tokens),
|
|
}
|
|
}
|
|
|
|
func addModelTokens(modelMap map[string]*model.ModelTokens, modelName string, tokens int64) {
|
|
if modelStat, ok := modelMap[modelName]; ok {
|
|
modelStat.Tokens += tokens
|
|
modelStat.Requests++
|
|
return
|
|
}
|
|
|
|
modelMap[modelName] = &model.ModelTokens{
|
|
Model: modelName,
|
|
Tokens: tokens,
|
|
Requests: 1,
|
|
}
|
|
}
|
|
|
|
func addDailyModelStat(models map[string]model.DailyModelStat, modelName string, tokens int64) map[string]model.DailyModelStat {
|
|
if models == nil {
|
|
models = make(map[string]model.DailyModelStat)
|
|
}
|
|
|
|
modelStat := models[modelName]
|
|
modelStat.Tokens += tokens
|
|
modelStat.Requests++
|
|
models[modelName] = modelStat
|
|
return models
|
|
}
|