cli/cmd/ai/ratelimit_dispatch.go
Charon 27d5e2e100 refactor: flatten commands, extract php/ci to own repos (#2)
## Summary
- Extract PHP/Laravel commands to `core/php` repo (42 files, standalone module)
- Extract CI/release + SDK commands to `core/ci` repo (10 files)
- Remove `internal/variants/` build tag system entirely
- Move all 30 remaining command packages from `internal/cmd/` to top-level `cmd/`
- Rewrite `main.go` with direct imports — no more variant selection
- PHP and CI are now optional via commented import lines in main.go

Co-authored-by: Claude <developers@lethean.io>
Reviewed-on: #2
Co-authored-by: Charon <charon@lthn.ai>
Co-committed-by: Charon <charon@lthn.ai>
2026-02-16 14:45:06 +00:00

49 lines
1.3 KiB
Go

package ai
import (
"context"
"forge.lthn.ai/core/go/pkg/log"
"forge.lthn.ai/core/go/pkg/ratelimit"
)
// executeWithRateLimit wraps an agent execution with rate limiting logic.
// It estimates token usage, waits for capacity, executes the runner, and records usage.
func executeWithRateLimit(ctx context.Context, model, prompt string, runner func() (bool, int, error)) (bool, int, error) {
rl, err := ratelimit.New()
if err != nil {
log.Warn("Failed to initialize rate limiter, proceeding without limits", "error", err)
return runner()
}
if err := rl.Load(); err != nil {
log.Warn("Failed to load rate limit state", "error", err)
}
// Estimate tokens from prompt length (1 token ≈ 4 chars)
estTokens := len(prompt) / 4
if estTokens == 0 {
estTokens = 1
}
log.Info("Checking rate limits", "model", model, "est_tokens", estTokens)
if err := rl.WaitForCapacity(ctx, model, estTokens); err != nil {
return false, -1, err
}
success, exitCode, runErr := runner()
// Record usage with conservative output estimate (actual tokens unknown from shell runner).
outputEst := estTokens / 10
if outputEst < 50 {
outputEst = 50
}
rl.RecordUsage(model, estTokens, outputEst)
if err := rl.Persist(); err != nil {
log.Warn("Failed to persist rate limit state", "error", err)
}
return success, exitCode, runErr
}