Merge pull request #1 from thepeterstone/claude/local-oss-model-agents-MEBqj

Local OSS models as a third runner (epic)

2 files changed, 246 insertions, 0 deletions

diff --git a/internal/retry/backoff.go b/internal/retry/backoff.go
new file mode 100644
index 0000000..b91abc4
--- /dev/null
+++ b/internal/retry/backoff.go
@@ -0,0 +1,77 @@
+// Package retry provides exponential-backoff retry helpers used across the
+// codebase for rate-limit-aware HTTP/subprocess calls.
+package retry
+
+import (
+	"context"
+	"fmt"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+)
+
+var retryAfterRe = regexp.MustCompile(`(?i)retry[-_ ]after[:\s]+(\d+)`)
+
+const maxBackoffDelay = 5 * time.Minute
+
+// IsRateLimitError returns true if err looks like a transient rate-limit
+// (e.g. HTTP 429, "too many requests", "overloaded") that is worth retrying.
+func IsRateLimitError(err error) bool {
+	if err == nil {
+		return false
+	}
+	msg := strings.ToLower(err.Error())
+	return strings.Contains(msg, "rate limit") ||
+		strings.Contains(msg, "too many requests") ||
+		strings.Contains(msg, "429") ||
+		strings.Contains(msg, "overloaded")
+}
+
+// ParseRetryAfter extracts a Retry-After duration from an error message.
+// Returns 0 if no retry-after value is found.
+func ParseRetryAfter(msg string) time.Duration {
+	m := retryAfterRe.FindStringSubmatch(msg)
+	if m == nil {
+		return 0
+	}
+	secs, err := strconv.Atoi(m[1])
+	if err != nil || secs <= 0 {
+		return 0
+	}
+	return time.Duration(secs) * time.Second
+}
+
+// RunWithBackoff calls fn repeatedly on rate-limit errors, using exponential backoff.
+// maxRetries is the max number of retry attempts (not counting the initial call).
+// baseDelay is the initial backoff duration (doubled each retry).
+func RunWithBackoff(ctx context.Context, maxRetries int, baseDelay time.Duration, fn func() error) error {
+	var lastErr error
+	for attempt := 0; attempt <= maxRetries; attempt++ {
+		lastErr = fn()
+		if lastErr == nil {
+			return nil
+		}
+		if !IsRateLimitError(lastErr) {
+			return lastErr
+		}
+		if attempt == maxRetries {
+			break
+		}
+
+		delay := baseDelay * (1 << attempt)
+		if delay > maxBackoffDelay {
+			delay = maxBackoffDelay
+		}
+		if ra := ParseRetryAfter(lastErr.Error()); ra > 0 {
+			delay = ra
+		}
+
+		select {
+		case <-ctx.Done():
+			return fmt.Errorf("context cancelled during rate-limit backoff: %w", ctx.Err())
+		case <-time.After(delay):
+		}
+	}
+	return lastErr
+}
diff --git a/internal/retry/backoff_test.go b/internal/retry/backoff_test.go
new file mode 100644
index 0000000..a963fc2
--- /dev/null
+++ b/internal/retry/backoff_test.go
@@ -0,0 +1,169 @@
+package retry
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"testing"
+	"time"
+)
+
+// --- IsRateLimitError tests ---
+
+func TestIsRateLimitError_RateLimitMessage(t *testing.T) {
+	err := errors.New("claude exited with error: rate limit exceeded")
+	if !IsRateLimitError(err) {
+		t.Error("want true for 'rate limit exceeded', got false")
+	}
+}
+
+func TestIsRateLimitError_TooManyRequests(t *testing.T) {
+	err := errors.New("too many requests to the API")
+	if !IsRateLimitError(err) {
+		t.Error("want true for 'too many requests', got false")
+	}
+}
+
+func TestIsRateLimitError_HTTP429(t *testing.T) {
+	err := errors.New("API returned status 429")
+	if !IsRateLimitError(err) {
+		t.Error("want true for '429', got false")
+	}
+}
+
+func TestIsRateLimitError_Overloaded(t *testing.T) {
+	err := errors.New("API overloaded, please retry later")
+	if !IsRateLimitError(err) {
+		t.Error("want true for 'overloaded', got false")
+	}
+}
+
+func TestIsRateLimitError_NonRateLimitError(t *testing.T) {
+	err := errors.New("claude exited with error: exit status 1")
+	if IsRateLimitError(err) {
+		t.Error("want false for non-rate-limit error, got true")
+	}
+}
+
+func TestIsRateLimitError_NilError(t *testing.T) {
+	if IsRateLimitError(nil) {
+		t.Error("want false for nil error, got true")
+	}
+}
+
+// --- ParseRetryAfter tests ---
+
+func TestParseRetryAfter_RetryAfterSeconds(t *testing.T) {
+	msg := "rate limit exceeded, retry after 30 seconds"
+	d := ParseRetryAfter(msg)
+	if d != 30*time.Second {
+		t.Errorf("want 30s, got %v", d)
+	}
+}
+
+func TestParseRetryAfter_RetryAfterHeader(t *testing.T) {
+	msg := "rate_limit_error: retry-after: 60"
+	d := ParseRetryAfter(msg)
+	if d != 60*time.Second {
+		t.Errorf("want 60s, got %v", d)
+	}
+}
+
+func TestParseRetryAfter_NoRetryInfo(t *testing.T) {
+	msg := "rate limit exceeded"
+	d := ParseRetryAfter(msg)
+	if d != 0 {
+		t.Errorf("want 0, got %v", d)
+	}
+}
+
+// --- RunWithBackoff tests ---
+
+func TestRunWithBackoff_SuccessOnFirstTry(t *testing.T) {
+	calls := 0
+	fn := func() error {
+		calls++
+		return nil
+	}
+	err := RunWithBackoff(context.Background(), 3, time.Millisecond, fn)
+	if err != nil {
+		t.Errorf("want nil error, got %v", err)
+	}
+	if calls != 1 {
+		t.Errorf("want 1 call, got %d", calls)
+	}
+}
+
+func TestRunWithBackoff_RetriesOnRateLimit(t *testing.T) {
+	calls := 0
+	fn := func() error {
+		calls++
+		if calls < 3 {
+			return fmt.Errorf("rate limit exceeded")
+		}
+		return nil
+	}
+	err := RunWithBackoff(context.Background(), 3, time.Millisecond, fn)
+	if err != nil {
+		t.Errorf("want nil error, got %v", err)
+	}
+	if calls != 3 {
+		t.Errorf("want 3 calls, got %d", calls)
+	}
+}
+
+func TestRunWithBackoff_GivesUpAfterMaxRetries(t *testing.T) {
+	calls := 0
+	rateLimitErr := fmt.Errorf("rate limit exceeded")
+	fn := func() error {
+		calls++
+		return rateLimitErr
+	}
+	err := RunWithBackoff(context.Background(), 3, time.Millisecond, fn)
+	if err == nil {
+		t.Fatal("want error after max retries, got nil")
+	}
+	if calls != 4 {
+		t.Errorf("want 4 calls (1 initial + 3 retries), got %d", calls)
+	}
+}
+
+func TestRunWithBackoff_DoesNotRetryNonRateLimitError(t *testing.T) {
+	calls := 0
+	fn := func() error {
+		calls++
+		return fmt.Errorf("permission denied")
+	}
+	err := RunWithBackoff(context.Background(), 3, time.Millisecond, fn)
+	if err == nil {
+		t.Fatal("want error, got nil")
+	}
+	if calls != 1 {
+		t.Errorf("want 1 call (no retry for non-rate-limit), got %d", calls)
+	}
+}
+
+func TestRunWithBackoff_ContextCancellation(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	calls := 0
+
+	fn := func() error {
+		calls++
+		cancel()
+		return fmt.Errorf("rate limit exceeded")
+	}
+
+	start := time.Now()
+	err := RunWithBackoff(ctx, 3, time.Second, fn)
+	elapsed := time.Since(start)
+
+	if err == nil {
+		t.Fatal("want error on context cancellation, got nil")
+	}
+	if elapsed > 500*time.Millisecond {
+		t.Errorf("context cancellation too slow: %v (want < 500ms)", elapsed)
+	}
+	if calls != 1 {
+		t.Errorf("want 1 call before cancellation, got %d", calls)
+	}
+}