ollama-proxy/internal/cli/serve.go
Atte149 3963eede70 feat: ollama-proxy — multi-account Ollama Cloud reverse proxy
Go reverse proxy for ollama.com that balances requests across multiple
API keys with round-robin and failover on 429/5xx. Exposes both native
Ollama API (/api/*) and OpenAI-compatible (/v1/*) passthrough.

- Round-robin balancer with per-account cooldown (60s default)
- Pre-stream failover: 429 → cooldown + next account; 5xx → next account
- Streaming invariant: once 2xx starts streaming, no account switch
- SSE (text/event-stream) and NDJSON passthrough with http.Flusher
- CLI: accounts add/list/remove/set-base-url, serve, version
- Accounts stored in ~/.config/ollama-proxy/accounts.json (chmod 0600)
- systemd unit (User=dueattendant149, 127.0.0.1:11435, Restart=always)
- 43 tests (unit + integration with httptest upstream)
- opencode integration: custom provider 'ocp' with explicit model list
- Requires NO_PROXY=127.0.0.1,localhost when HTTP_PROXY is set
2026-06-19 13:58:13 +03:00

109 lines
2.9 KiB
Go

package cli
import (
"context"
"flag"
"fmt"
"log/slog"
"net/http"
"os"
"os/signal"
"syscall"
"time"
"github.com/Atte149/ollama-proxy/internal/config"
"github.com/Atte149/ollama-proxy/internal/log"
"github.com/Atte149/ollama-proxy/internal/proxy"
)
// RunServe starts the proxy HTTP server.
func RunServe(args []string) int {
fs := flag.NewFlagSet("serve", flag.ContinueOnError)
addr := fs.String("addr", "", "listen address (default 127.0.0.1:11435)")
baseURL := fs.String("base-url", "", "upstream root (default https://ollama.com)")
cooldown := fs.Duration("cooldown", 0, "per-account 429 cooldown window")
retries := fs.Int("retries", 0, "max failover attempts")
logLevel := fs.String("log-level", "", "debug|info|warn|error")
if err := fs.Parse(args); err != nil {
fmt.Fprintln(os.Stderr, err)
return 2
}
cfg := config.DefaultServerConfig()
if *addr != "" {
cfg.Addr = *addr
}
if *baseURL != "" {
cfg.BaseURL = *baseURL
}
if *cooldown > 0 {
cfg.Cooldown = *cooldown
}
if *retries > 0 {
cfg.Retries = *retries
}
if *logLevel != "" {
cfg.LogLevel = *logLevel
}
cfg.ApplyEnv()
if err := cfg.Validate(); err != nil {
fmt.Fprintln(os.Stderr, "config error:", err)
return 2
}
logger := log.New(cfg.LogLevel)
af, err := config.LoadAccounts()
if err != nil {
logger.Error("load accounts failed", "err", err)
return 1
}
if len(af.Accounts) == 0 {
logger.Error("no accounts configured; run `ollama-proxy accounts add` first")
return 1
}
// Per-file BaseURL override wins over flag/env when set.
if af.BaseURL != "" {
cfg.BaseURL = af.BaseURL
}
balancer := proxy.NewBalancer(af.Accounts, cfg.Cooldown)
handler := proxy.NewHandler(balancer, cfg.BaseURL, cfg.Retries, logger)
srv := &http.Server{
Addr: cfg.Addr,
Handler: handler,
// No ReadTimeout/WriteTimeout: streaming chat may be idle for long
// periods between tokens. The http.Server's default idle timeout (60s)
// applies between reads; if that becomes a problem we'll add a per-read
// deadline via a wrapped Transport, not a global timeout.
}
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
defer stop()
go func() {
logger.Info("ollama-proxy starting",
"addr", cfg.Addr, "upstream", cfg.BaseURL,
"accounts", balancer.Len(), "cooldown", cfg.Cooldown.String(),
"retries", cfg.Retries, "log_level", cfg.LogLevel)
if err := srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
logger.Error("server error", "err", err)
stop()
}
}()
<-ctx.Done()
logger.Info("shutdown signal received, draining…")
shutdownCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
if err := srv.Shutdown(shutdownCtx); err != nil {
logger.Error("graceful shutdown failed", "err", err)
return 1
}
logger.Info("stopped")
return 0
}
// keep slog referenced even if logger.go ever drops it
var _ = slog.LevelInfo