fix: retry on transient LLM response body truncation

Addresses intermittent 'unexpected end of JSON input' failures where the
LLM response body is truncated in transit between the proxy and client.

Root cause: network-level truncation where io.ReadAll returns partial data
(observed in 3/50 CI runs through HAI proxy). The response body reading
was already using io.ReadAll correctly, but transient network issues
between the proxy and client can still cause partial reads.

Changes:
- Add Content-Length validation in doRequest: detect when fewer bytes
  arrive than the server declared, triggering a retry
- Add retry logic in Complete: retries once on retryable errors (body
  read failures, content-length mismatches) with a 500ms backoff
- Add parse-level retry in main: if ParseResponse fails, re-requests
  from the LLM once before giving up (defensive, since retries always
  succeed per issue evidence)
- Improve ParseResponse error diagnostics: log raw vs cleaned lengths
  and a preview of the cleaned content to aid future debugging

Does NOT retry on API errors (4xx/5xx) or structural issues — only
transient body read problems.

Closes #47

llm/client.go

@@ -75,12 +75,52 @@ type Message struct {
 // Complete sends a chat completion request and returns the assistant's response content.
 // The first message with role "system" is treated as the system prompt.
 func (c *Client) Complete(ctx context.Context, messages []Message) (string, error) {
-	switch c.provider {
-	case ProviderAnthropic:
-		return c.completeAnthropic(ctx, messages)
-	default:
-		return c.completeOpenAI(ctx, messages)
+	var result string
+	var err error
+
+	for attempt := 0; attempt < 2; attempt++ {
+		switch c.provider {
+		case ProviderAnthropic:
+			result, err = c.completeAnthropic(ctx, messages)
+		default:
+			result, err = c.completeOpenAI(ctx, messages)
+		}
+
+		if err == nil {
+			return result, nil
+		}
+
+		// Only retry on response body read errors (transient network issues).
+		// Do not retry on context cancellation, status errors, or parse errors
+		// that indicate a structural API problem.
+		if !isRetryableError(err) {
+			return "", err
+		}
+
+		if attempt == 0 && ctx.Err() == nil {
+			// Brief pause before retry to allow transient issues to resolve.
+			time.Sleep(500 * time.Millisecond)
+		}
 	}
+
+	return "", err
+}
+
+// isRetryableError returns true for transient errors worth retrying.
+func isRetryableError(err error) bool {
+	if err == nil {
+		return false
+	}
+	s := err.Error()
+	// Body read failures (connection reset, truncation)
+	if strings.Contains(s, "read response") {
+		return true
+	}
+	// Unexpected body length (our content-length validation)
+	if strings.Contains(s, "body length mismatch") {
+		return true
+	}
+	return false
 }
 
 // --- OpenAI-compatible implementation ---
@@ -231,6 +271,12 @@ func (c *Client) doRequest(req *http.Request, parse func([]byte) (string, error)
 		return "", fmt.Errorf("read response: %w", err)
 	}
 
+	// Validate body length against Content-Length header when present.
+	// A mismatch indicates the response was truncated in transit.
+	if cl := resp.ContentLength; cl > 0 && int64(len(body)) < cl {
+		return "", fmt.Errorf("body length mismatch: Content-Length=%d, received=%d", cl, len(body))
+	}
+
 	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
 		return "", fmt.Errorf("LLM API error (status %d): %s", resp.StatusCode, string(body))
 	}